AUTOMATED INTELLIGENT SYSTEM FOR ONLINE MARKET

FORECASTS USING STATISTICAL MODEL

BY

SAKPOBA OGHENEFEJIRO DELPHINE

FOS/19/20/258510

A PROJECT WORK IS SUBMITTED TO

THE DEPARTMENT OF COMPUTER SCIENCE,
FACULTY OF SCIENCE,
DELTA STATE UNIVERSITY, ABRAKA, DELTA STATE.

IN PARTIAL FULFILMENT OF THE REQUIREMENTS FOR

THE AWARD OF BACHELOR OR SCIENCE(B.Sc.)
DEGREE IN COMPUTER SCIENCE.

OCTOBER, 2023

I
 CERTIFICATION
This is to certify that this project work, “Automated Intelligent System for Online
Market Forecasts Using Statistical Model”, was carried out by SAKPOBA
OGHENEFEJIRO DELPHINE with Matriculation number FOS/19/20/258510
under the supervision of Dr. F.O. Okorodudu and was submitted to the department of
Computer Science, Delta State University, Abraka.

………………………………… ………………………….
Dr. F.O. Okorodudu DATE
(Project Supervisor)

………………………………… ………………………….
Dr. Edje E. Abel DATE
(Head of Department)

ii
 DEDICATION

This work is dedicated to God for his enabling grace. I also dedicate this project to my
parents and siblings for their financial and emotional support and lastly to all
computer enthusiasts who help to make life a pleasant experience.

III
 ACKNOWLEDGEMENT

I would like to express my profound gratitude to God Almighty for His guidance and
provision towards the completion of my project work. My sincere gratitude goes to
my Project Supervisor, Dr. F.O. Okorodudu, for his unmatched efforts, valuable
contributions, and insightful feedback throughout the entire research process.

Furthermore, I would like to thank the Head of the Department of Computer Science,
Dr. Abel Edje, and the other lecturers who work tirelessly to groom myself and my
colleagues in the best way possible.

I am also thankful to my friends, CHIOMA, JENNIFER & ESE, more gratitude goes
to AKHABUE KELVIN, AKPODINYO OGHENETEGA & OKE PEACE for their
encouragement, feedback and assistance, which greatly enriched my project.

Lastly, I extend my sincere thanks and appreciation to my parents and my sisters, Mr.
& (Mrs.)SAKPOBA, RUKEVWE & TEGA, for their emotional and financial support
throughout my academic journey.

IV
 ABSTRACT

Online markets have witnessed exponential growth in recent years, presenting both
challenges and opportunities for businesses operating in the digital space. Accurate
market forecasting is crucial for making informed decisions, optimizing resource
allocation, and gaining a competitive edge. This seminar focuses on leveraging
automated intelligent systems powered by statistical models, specifically linear
regression, to forecast market trends in online domains.
The seminar begins by providing an overview of the challenges faced in online
markets, including rapidly changing consumer behaviors, dynamic pricing strategies,
and intense competition. Traditional forecasting methods often struggle to capture the
intricacies of these complex environments, necessitating the integration of intelligent
systems to enhance accuracy and efficiency.
The core focus of this seminar is the application of linear regression, a well-
established statistical model, in online market forecasting. Linear regression offers a
flexible framework for analyzing relationships between various market variables and
predicting future outcomes. It provides a foundation for automated systems to
leverage historical data, extract meaningful patterns, and generate reliable forecasts.

V
 TABLE OF CONTENT

CERTIFICATION Error! Bookmark not defined.

DEDICATION Error! Bookmark not defined.
ACKNOWLEDGEMENTS Error! Bookmark not defined.
ABSTRACT Error! Bookmark not defined.

CHAPTER ONE: INTRODUCTION

1.1 Background to the Study
1.2 Statement of the Problem

1.3 Aim and Objectives of the Study

1.4 Significance of the Study

1.5 Scope of the Study

1.6 Limitation of the Study

CHAPTER TWO: LITERATURE REVIEW

2.1 Introduction
2.2 Conceptual Review of Marketing Information System
2.3 The Strategic Role of the Marketing Information Systems
2.4 The Role of the Internet
2.5 Benefits of the Marketing Information System
2.6 Marketing Information System Functional Components
2.7 Marketing Decision Support System
2.8 Theoretical Review
2.8.1 Advantages of Market Forecasting System
2.8.2 Market Forecasting System Web Portal
2.8.3 Types of Market Forecasting System Web Portal
2.8.4 Database for Market Forecasting System
2.8.5 Merits of Integrating Databases in Web Applications
2.8.6 Roles of a Database Administrator
2.8.7 Database Query Market Forecasting System
2.9 Review of Related Literature

VI
CHAPTER THREE: METHODOLOGY AND SYSTEM ANALYSIS
SYSTEM ANALYSIS AND DESIGN
3.1 Methodology Adopted
3.1.1 Problem Identification Using SSADM
3.2 Analysis of the Existing System
3.2.1 Dataflow of the Existing System
3.2.2 Disadvantages of the Existing System
3.2.3 Weakness of the existing System
3.3 Feasibility Study
3.3.1 Economic Feasibility
3.3.2 Technical Feasibility
3.3.3 Operational Feasibility
3.4 Analysis of the Proposed System
3.4.1 Data Flow Diagram of the Proposed System
3.4.2 Advantages of the Proposed System
3.4.3 Justification of the Proposed System
3.5 Functional Requirements
3.5.1 Use Case Diagram of the Admin / User Privileges
3.6 Data Requirements
3.7 High Level Model of the Proposed System

CHAPTER FOUR: SYSTEM DESIGN AND IMPLEMENTATION

SYSTEM DESIGN AND IMPLEMENTATION
4.1 Objectives of the Design
4.2 System Specifications
4.2.1 Math Specifications
4.2.2Programming Module Specification
4.2.3 Input and Output Format
4.2.4 Database Specification and Design
4.2.5 Algorithm
4.2.6 Data Dictionary

VII
4.4 System Flowchart
4.5 System Implementation
4.5.1 System Requirements
4.5.2 Hardware Requirements
4.5.3 Software Requirements
4.5.4 Program Development
4.5.5 System Testing
4.5.6 Training
4.5.7 Documentation
4.5.8 System Conversion

CHAPTER FIVE: SUMMARY, CONCLUSION AND RECOMMENDATION

5.1 Summary
5.2 Conclusion
5.3 Recommendations
5.3.1 Application Areas
5.3.2 Suggestion for Further Research

REFERENCES
Appendix A: Source Code
Appendix B: Questionnaire

VIII
 CHAPTER ONE

INTRODUCTION

1.1 Introduction

Forecasting is the process of making predictions of the future based on past and present

data and analysis of trends. Computerization of the store can remove wastage, guarantee

quick service at service points of vital importance to the public and improve productivity.

Such computerization effort often costs for less than the money and time it will save both

the public and the organization. Computers will remain an integral part of life; this is as a

result of increasing number of areas where they have become indispensible. Worthy of

note also is the fact that business decision making relies heavily on market competition,

this makes market forecasting very important in business planning (Makridakis, S., &

Wheelwright, S. C. (1977).

Market forecasting projects future numbers, characteristics and trends in your target

market. It is of great importance to business owners, market practitioners, etc. As a new

application emerges computer practitioners are challenged and new systems or

applications that address these new identified problems are designed and implemented.

Sometimes, post implementation requirements crop up making modifications to already

developed applications inevitable or engendering the need for a new application that

encompasses all the requirements altogether (Wheelwright, S. C., & Clark, K. B. (1992).

1
1.2 Background of Study

Online marketing have gained in popularity with the FOREX markets top on the list of

trades that have been widely utilized. More formally, online marketing refer to any form

of trading i.e. buying and selling including advertising that take place over the internet.

Online markets are a way of making business more convenient for businesses which may

be far away from one another. Through distant communication networks such as

telecommunication, sub-sea optical fiber links and web programs over the internet

framework these form of marketing have been made possible. In recent times there have

been calls to make online marketing more intelligent, in particular helping businesses to

survive stiff competition over the internet. We see this as a challenge since there is vast

amount of online markets with a heavy presence on the internet (Chaffey, D., & Smith, P.

R. (2022).

Forecasting is fundamental in any planning effort (Chase, R. (2014). In the short term,

forecast is needed to predict the material, products, services or other resources to respond

to changes in demand. A forecast allows adjusting schedules and varying labor and

materials. In the long run, it is required to predict the basis for strategic changes, such as

the development of new markets, new products or services and expand or build new

facilities.

Effective planning, in short and long term, depends on demand forecasts for the company

products (Heizer, J. (2009). Good forecasts are crucial to all business aspects: Demand

forecast is the only useful data until the actual demand is known. Therefore, demand
2
forecasts guide decisions in many areas: human resources, capacity management and

supply chain.

Sales and operations planning is a process that helps to provide better customer service,

handling of lower inventories, offer shorter delivery time to customers, stabilize

production rates and facilitate management business. It does not matter that, owing to

changing markets, the chemicals supplying enterprises have troubles with operations

scheduling and inventories management; they are a fundamental component in the

national economy (Shah, N. K., Li, Z., & Ierapetritou, M. G. (2011).

The chemicals supplying enterprises demands are highly variable in volume and

presentation; their customers vary from a small hardware store, up to an auto assembler

factory, passing through: pharmaceutical, chemical, petrochemical and polymer

companies, paints and varnishes manufacturers, etc. In some companies, they handled up

to 500 different materials and have up to 1000 clients; all of this complicates their

operations planning.

Because of the above chemicals supplying enterprises problems, a system to forecast their

sales with the best possible accuracy is proposed. The system, (algorithm and software)

for the yearly or monthly sales prediction, calculates a possible sales number for each

product using five techniques, evaluates the error of each of them and selects the lowest

error technique; from which the sales forecast for each product is proposed. The goal is to

make effective plans in order to properly satisfy the customer demands (Umble, E. J.,

Haft, R. R., & Umble, M. M. (2003).

3
1.3 Statement of Problem

Investigation revealed that Statistical models have been useful in solving a variety of

tasks. However, in online marketing forecasts this is yet to be fully realized. Thus, there is

need to improve on existing models or invent new ones that can help online markets

predict or forecast best market scenarios and avoid huge financial losses.

The above problems discovered therefore prompted to a software design to be able to add

to existing stock and delete goods in stock collectively referred to as updating, as well as

producing an accurate accounting system for the STORE.

1.4 Aim and Objectives of the Study

Aim

The aim of the study is to design and implement an Automated Intelligent System for

Online Market Forecasts Using Statistical Model. In achieving this aim, the following

specific objectives were laid out as follows to design and develop an application software

that will:

Specific Objectives

i. Provide software interface for monitoring and control of online markets;

ii. Automate customer, product, and supplier management on the system;

iii. Enables business owners predict future business trends; and

iv. Improve existing statistical model for intelligently forecasting online market trends.

4
1.5 Significance of Study

This study will expand the already rich body of knowledge in online market forecast. It

will be useful for businesses on the internet to accurately predict business trends for profit

maximization and loss reduction. In this research work will provide a reliable way of

handling product price forecasting to forecast product prices in and financial institution.

Furthermore, it will aids structural document representation and eliminates the tedium of

performing monotonous transaction.

This research will also contribute to existing literature in this area and will serve as a

guild or blueprint for an undergraduate student. Automated Intelligent System for Online

Market Forecasts Using Statistical Model help organization to predict achievable sales

revenue, efficiently allocate resources, Plan for future growth etc. As your business

grows, sales forecasts continue to be an important measurement of a company’s health.

Wall Street measures the success of a company by how well it meets its quarterly sales

forecasts and the overall effect of accurate Product Price Forecasting is a business that

runs more efficiently, saving money on excess inventory, increasing profit and serving its

customers better.

1.6 Scope of Study

The scope of this research is focused on the Design and Implementation of an Automated

Intelligent System for Online Market Forecasts Using Statistical Model (Linear

Regression). This study is limited to online markets of goods and services.

5
1.7 Limitations of the Study

During the course of this study, many things militated against its completion, some of

which are:

i. Time Constraint: The time frame given to accomplish this project was very short

due to school academic calendar and it was carried out under pressure which made

the researcher not to implement some necessary features.

ii. Research material: availability of research material is a major setback to the scope

of the study.

iii. Frequent power failure: This made the researcher append more money on fuel to

ensure sustainable power.

iv. Financial Constraint: Insufficient fund tends to impede the efficiency of the

researcher in sourcing for the relevant materials, literature or information and in the

process of data collection (internet).

1.8 Definition of Terms

Computer: A system software package that converts a problem oriented language to the

language a computer understands. It’s an electronic data processing machine which can

store and process information at very high speeds.

Algorithm: A logical of instructions, which are carried out in a fixed order to find the

solution to a problem.

Computerization: The use of computer to control an operation or system.

6
Data: These are units of observation which do not curvy any meaning

DOS: An operating system that uses disk devices for permanent storage.

Information: Consists of facts resulting from processed data, providing knowledge

relating to events or situation.

Password: A secret word, which one has to know before he can access to a particular

system.

Program: Set of instruction, which is used to solve a problem.

Flowchart: A diagram in which particular shapes and connecting lines are used for

showing how each particular action in a system is connected with one another.

7
 CHAPTER TWO

LITERATURE REVIEW

2.1 Introduction

This chapter focuses on the review of related literature. A literature review includes the

current knowledge as well as theoretical and methodological contributions to a particular

topic. It documents the state of the art with respect to the topic you are writing. It surveys

the literature in the topic selected. In this research work the literature review includes the

Conceptual Review of Marketing Information System, Strategic Role of the Marketing

Information Systems, Role of the Internet, Benefits of the Marketing Information System,

Marketing Information System Functional Components, Marketing Decision Support

System, Theoretical Review and Review of Related Literature.

2.2 Conceptual Review of Marketing Information System

Simply put, a Marketing Information System (MkIS) is a computerized system that is

designed to provide an organized flow of information to enable and support the marketing

activities of an organization. The MkIS serves collaborative, analytical and operational

needs. In the collaborative mode, the MkIS enables managers to share information and

work together virtually. In addition, the MkIS can enable marketers to collaborate with

customers on product designs and customer requirements. The analytical function is

addressed by decision support applications that enable marketers to analyze market data

8
on customers, competitors, technology and general market conditions. These insights are

becoming the foundation for the development of marketing strategies and plans. The

MkIS addresses operational needs through customer management systems that focus on

the day-to-day processing of customer transactions from the initial sale through customer

service (Harmon, R. R. (2002).

MkIS systems are designed to be comprehensive and flexible in nature and to integrate

with each other functionally. They are formal, forward looking and essential to the

organization’s ability to create competitive advantage. The MkIS is the firm’s “window

on the world” and, increasingly, it is the primary customer interface. Figure 1 presents the

basic architecture of the MkIS.

2.3 The Strategic Role of the Marketing Information Systems

Historically, the role of the marketing function has been to support “make and sell”

business strategies that emphasized increases in market share over the creation of long-

term customer value. This view started to change after World War II with the recognition

that satisfying the customer’s needs and wants should be the focus of a firm’s business

activities (Harmon, R. R. (2002).

The emphasis on the customer elevated the importance of marketing as a core business

function on a par with research and development and production. The marketing function
9
has become the firm’s window to the world in the sense that it must monitor the

marketing environment for changes in buyer behavior, competition, technology,

economic conditions, and government policies. Marketing is a “strategic” function in that

marketing activities enable organizations to identify and adapt to changes in the market

environment (Day, G. S. (2011)

The strategic function of marketing is further emphasized as Internet-based technologies

have enabled radically new approaches to selling where information technology for the

first time touches customers and provides new means for collecting marketing

information. In a knowledge-intensive economy, the ability to collect, analyze and act

upon marketing information more rapidly than the competition is the core competency

from which competitive advantage flows. Marketing information systems provide the

information technology backbone for the marketing organization’s strategic operations. In

a broader sense, the MkIS creates an organized and timely flow of information required

by marketing decision makers. It involves the equipment, software, databases, and also

the procedures, methodologies and people necessary for the system to meet its

organizational objectives. MkIS encompasses a broad spectrum of activities from simple

transaction processing complex marketing strategy decision making (Bhutia, C. D.,

Shilpa, R. G., & Sharma, P. (2011).

10
2.4 The Role of the Internet

Information technology has transformed how firms conduct business. For example,

financial service providers such as banks, stockbrokers and insurance companies could

not do business today without their client-server-based information technology. This

technology has long supported marketing activities. However, it is the recent advent of

the Internet, and especially the browser- based World Wide Web, which has ignited a

revolution in MkISs (Harmon, R. R. (2002).

The term “cybermarketing” is often used to describe the Internet’s convergence of

computers, information systems, telecommunications and the customer with the

marketing process. Internet marketing is characterized by interactivity, graphical user

interfaces, multimedia content, and one-to-one connectivity. Internet technologies are not

only providing new ways to reach the customer, but also to enable the reengineering of

the entire marketing process and, indeed, the entire enterprise. It is no longer acceptable

to view marketing as a standalone activity with lengthy time lapses between product

concept, marketing strategy and commercialization. Marketing has become interactive

and real time (Harmon, R. R. (2002).

The rapidly growing field of marketing automation encompasses customer management

functions to support e-commerce. As depicted in Figure 2, customer management

applications include marketing decision support systems, customer relationship

management, sales force automation, customer service and e-commerce activities. These

activities are often described as “front office” customer-oriented activities. “Back office”
11
enterprise resource planning (ERP) activities include manufacturing, finance and human

resources. “Supply chain management” (SCM) activities encompass electronic

procurement, inventory management, quality management and logistics systems to link an

organization with its suppliers. These three elements comprise the enterprise information

system (Lankford, W. M. (2004).

Large integrated enterprise software companies such as Oracle, SAP, PeopleSoft, and

IBM address all three major applications and they are beginning to use Web-based

technologies to redesign business processes throughout the organization. The result is

leaner organizations, faster response times, and lower costs. Decision- makers are able to

integrate information from customers, suppliers, and the internal organization to obtain an

enterprise-wide view of their ability to develop and execute marketing strategy. Until

truly integrated browser-based systems are widely in use, the principal challenge for

marketers is to tie e-commerce generated data with legacy information systems in order to

create a unified view of each customer. Marketers will need to understand all the various

ways that customers are touching the business through existing interfaces and e-

commerce. Many of the older interfaces, such as telemarketing centers, point of sale

(POS) systems, and the sales force are likely to be supported by legacy client-server

technology. Marketers need to consolidate data from those systems with that from the

Web-based e- commerce sources into a holistic view of the customer and make it

available to decision- makers (Harmon, R. R. (2002).

12
2.5 Benefits of the Marketing Information System

The MkIS increases the number of options available to decision-makers and supports

every element of marketing strategy. MkIS affects marketing’s interfaces with customers,

suppliers and other partners. The primary benefits of the MkIS impact in the areas of

functional integration, market monitoring, strategy development, and strategy

implementation.

1. Market Monitoring: Through the use of market research and marketing

intelligence activities the MkIS can enable the identification of emerging market

segments, and the monitoring of the market environment for changes in consumer

behavior, competitor activities, new technologies, economic conditions and

governmental policies. Market research is situational in nature and focuses on

specific strategic or tactical marketing initiatives. Marketing intelligence is

continuous in nature and involves monitoring and analyzing a broad range of

market-based activities and information sources. There are three major sources of

market information (Harmon, R. R. (2002).

The first is syndicated data published by market research companies and industry

associations. Company-sponsored primary research is another option. It is much

more focused since you ask specific questions of respondents within your markets.

But, it is considerably more expensive and time consuming. Perhaps the best data

available are your own customer’s behavior captured from web site viewing, point

13
 of sale (POS) transactions, and systematic feedback from the sales force(Omar, A.

A. (2017)

2. Strategy Development: The MkIS provides the information necessary to develop

marketing strategy. It supports strategy development for new products, product

positioning, marketing communications (advertising, public relations, and sales

promotion), pricing, personal selling, distribution, customer service and partnerships

and alliances. The MkIS provides the foundation for the development information

system-dependent e-commerce strategies (Harmon, R. R. (2002).

3. Strategy Implementation: The MkIS provides support for product launches,

enables the coordination of marketing strategies, and is an integral part of sales

force automation (SFA), customer relationship management (CRM), and customer

service systems implementations. The MkIS enables decision- makers to more

effectively manage the sales force as well as customer relationships. Some customer

management software companies are extending their CRM applications to include

partner relationship management (PRM) capabilities. This has become increasingly

important as many marketers are choosing to outsource important marketing

functions and form strategic alliances to address new markets (Harmon, R. R.

(2002).

4. Functional integration: The MkIS enables the coordination of activities within the

marketing department and between marketing and other organizational functions

14
 such as engineering, production, product management, finance, manufacturing,

logistics, and customer service.

2.6 Marketing Information System Functional Components

Marketing Information System consists of four major components as shown below in

figure 1.1:

(1) User interfaces,

(2) Applications software,

(3) Databases, and

(4) Systems support.

User Interfaces: The essential element of the MkIS is the managers who will use the

system and the interfaces they need to effectively analyze and use marketing information.

The design of the system will depend on what type of decisions managers need to make.

The interface includes the type of hardware that will be used, the way information is

analyzed, formatted and displayed, and how reports are to be compiled and distributed.

Issues to resolve are ease of use, security, cost, and access.

The figure below depicts the relationship between one device to the other. The user login

to the network, enter the data and process it with a support from the customer unit.

15
 Figure 1.1: Depicts the relationship between MkIS Functional Components

Applications Software: These are the programs that marketing decision makers use to

collect, analyze, and manage data for the purpose of developing the information necessary

for marketing decisions. Examples include the marketing decisions support software

(MDSS) and customer management software for on-line sales and customer service.

Figure 1.1 shows the relation between the functional components.

Marketing Databases: A marketing database is a system in which marketing data files

are organized and stored. Data may be collected from internal and external sources.

Internal sources largely result from transactions. They provide data from e-commerce

sites, sales results, shipping data, inventories, and product profitability. External sources

16
include market research, competitor intelligence, credit bureaus, and financial institutions.

Data can be organized in a flat file (Text file with one data record per line) or a relational

database (Data is stored in tabular form where each row represents one entity and each

column represents one characteristic of that entity). For instance, each row could

represent a customer with the columns providing name, identification number, and

purchase information (Harmon, R. R. (2002).

System Support: This component consists of system managers who manage and

maintain the systems assets including software and hardware network, monitor its

activities and ensure compliance with organizational policies. This function may also

include a help desk for system users (Harmon, R. R. (2002).

2.7 Marketing Decision Support System

Marketing decision support systems (MDSS) constitute a set of core applications of the

MkIS. The MDSS provides computer-based tools, models, and techniques to support the

marketing manager’s decision process. In the general case, MDSS is optimized for

queries of historical data.

MDSS data typically are derived from both internal and external market sources. The

MDSS features inquiry and report generation functions where the manager can access

marketing data, analyze it statistically, and use the results to determine an optimal course

of action (Harmon, R. R. (2002).

17
A. Marketing Decisions Support System Functions: The MDSS can provide

analytical models for forecasting, simulation, and optimization. MDSS tools

include simple spreadsheets such as Excel, statistical analysis packages such as

SPSS and SAS, on-line analytical processing (OLAP) tools, data mining

applications, and neural networks. The MDSS provides the user with the ability to

explore multiple options (Harmon, R. R. (2002). Typical MDSS functions

include models and tools for:

1. Sensitivity analysis. Decision-makers can explore changes in a strategic

variable such as price and model its impact on demand or competitive

behavior.

2. What-if analysis. Can be easily accomplished with a spreadsheet. Revenues

and costs can be manipulated to show the impact of each variable on profits

and cash flows.

3. Goal setting. Analysis focuses on the desired result and builds the resource

base necessary to accomplish the goal.

4. Exception reporting. Analysis looks for results that exceed or fall short of

stated goals or benchmarks. Which products or segments exceeded sales

forecasts? Sometimes called gap analysis.

5. Pareto analysis. Analysis looks for activities that generate disproportionate

results. For instance, the top 20 percent of customers may account for 80

percent of sales revenues.

18
 6. Forecasting models. Econometric models are used to analyze time series

data for the purpose of predicting future sales and market share levels.

7. Simulation models. Monte Carlo simulations address marketing decision

making under conditions of uncertainty. Variables such as the market price,

unit variable cost, and quantity sold are not known ahead of the product

investment decision. Simulation models allow the marketer to analyze risk

and assess the probabilities of likely outcomes of their decisions.

8. Scorecards and dashboards. Scorecard systems can present a consistent

framework for tracking the effectiveness of marketing activities. They often

have different modules for senior executives, marketing managers, product

managers, and customer service managers. Scorecard systems allow the

user to “drill down” on an analytic and workflow basis to determine the

status of any strategic initiative. Dashboards allow frontline managers to

monitor their critical performance indicators. These systems are often used

in conjunction with “best practice” standards for call-center-based customer

support.

B. MDSS Analyses: Marketers typically use MDSS models and tools to analyze

markets, customers, competitors, and internal operations (Harmon, R. R. (2002).

The following list presents some of the most common types of issues targeted by

MDSS analyses.

19
1. Market segment analysis. Use of modeling techniques to identify segments

and analyze economic trends, demographics and behavior.

2. Market share analysis. Analyze trends and determinants of market share.

3. Competitor analysis. Analysis of competitors’ market positions, economics

customer base, and marketing strategies.

4. Pricing analysis. Identifies and analyzes the factors that influence a firm’s

ability to set prices including price elasticity and demand analysis. Includes

internal economics and market related factors.

5. Cost analysis. Studies a firm’s overall cost structure and its impact on product

cost. Margin analysis combines cost analysis with pricing analysis. Variance

analysis looks for explanations of costs overages and underages.

6. Sales analysis. Studies the distribution of a firm’s sales by region, product,

brand, sales territory, etc.

7. Sales forecasting. Develops estimates of sales potential by product, region,

sales territory, brand, etc.

8. Sales force productivity. Studies sales force effectiveness and efficiency and

contributing factors.

9. Advertising analysis. Analyzes advertising effectiveness, media choices and

brand awareness.

20
 10. Distribution. Analyzes channel decisions from economic and strategic

perspectives.

11. Simulation. Simulates decision making under various strategic scenarios.

12. Customer satisfaction. Analyzes issues concerning the customer’s expectations

and outcomes with the product.

C. Data Warehousing: IBM defines a data warehouse as a place that stores

enterprise data designed to facilitate management decisions. In essence, a data

warehouse provides the basis for an analytical system where periodic data points

are collected and stored at specified times for future analysis. Data warehousing

enables marketers to capture, organize, and store potentially useful data about

customers and markets for decision-making purposes (Harmon, R. R. (2002).

Every record of a transaction or interaction with a customer, supplier, channel

member, or sales person is an opportunity to create knowledge. Firms collect data

from these day-to- day business operations. In order for this data to be useful, it is

often organized and stored in a data warehouse. Simply put, a marketing data

warehouse is a repository for data that has been collected from internal and

external data sources. Each customer generates a stream of transaction records

over time. Data sources may include scanner data, billing records, applications,

registration forms, warranty forms, call reports, customer service inquiries, and

web site data. Data warehousing enables the firm to organize and store this data
21
 for analysis purposes. By careful analysis of this and other data, firms can design

more effective and efficient ways to serve their customers. Data warehouses exist

to support the decision-making process by providing ready access to market and

customer data (Harmon, R. R. (2002)

The Internet has shifted power away from marketers to customers by lowering

search costs and providing greater choice. Competitors are only a “click” away.

Consequently, marketers need to work smarter to create and manage the one-to-

one relationships that customers desire. This goal requires increased knowledge

about customer preferences, behaviors, and value expectations in order to create

better products and services. Conversely, marketers need to understand which

customers are the most valuable to them over time. They need to regularly

monitor and evaluate the “lifetime value” of each customer in order to determine

which customers to continue investing in and which ones to drop (Harmon, R. R.

(2002).

2.8 Theoretical Review

The related studies below serves as supporting details about the impact of computerized

payment system (Market Forecasting System). In the case study of Bitwabado (2011), he

focused on computerized a Market Forecasting Systems and cash management in

financial institutions. The study addressed objectives, benefits, problems associated with

computerization, how cash is managed, impact of computerized accounting on cash

22
management as well as the relationship between two variables and coming up with the

recommendations to the stake holders of the bank. Descriptive and analytical research

was used to examine findings and come up with conclusions. Stratified random and

purposive sampling was used to select elements from the different departments and levels

of management with a sample size of 31 respondents. Questionnaires, interviews,

sampling and use of related literature from text books, journals, magazines and internet

were also used. The findings of the study indicated that though computerized payment

systems have impact on cash management, the relationship is weak sending an overall

negative signal to the stake holders and management that computerized accounting alone

cannot fully manage institutional cash but also strengthening other means because there

are some activities which cannot be detected by computers such as money laundering and

other related activities which requires tight supervision from the management. Also the

research of Dacosta (2012) was organized to assess the impact of the use of Computerized

Accounting Systems in financial reporting of rural banks in Ghana. The study also had

another objective of bringing out the problems encountered in the use of a computerized

payment System. Advancement in technology is now the order of the day. Businesses are

constantly looking for cost-effective, economic and efficient ways of satisfying

customers’ needs. Thus, there is the need for businesses to be abreast of the current issues

in technology to enhance their business. This is to help gain a competitive advantage over

their competitors especially in this era where there are more banks springing up. One of

the ways to reduce cost in business processes is to ensure that resources allocated are well
23
utilized to obtain maximum benefits at minimum cost. Thus with the use of a resource

(input) like a Computerized Market Forecasting System, it is expected that, the

accounting system will be able to generate relevant and useful reports (output) for making

economic decisions by users. Computerized Accounting Systems are therefore used by

these organizations in order to generate timely and accurate reports through a fast and

efficient processing of accounting data. The study of Dacosta (2012) revealed that

because of the numerous benefits that are associated with computerized Market

Forecasting System more importantly its ability to produce and present relevant and

faithful representative financial reports to end users.

2.8.1 Advantages of Market Forecasting System

Most companies use manual or computerized accounting to track expenditures and

income. Assets, liabilities, revenue, expenses and equity must be documented and

transferred to a general ledger containing the company’s financial details. Such

information may be analyzed to help business owners make future financial decisions,

using the advantages of either manual or computerized accounting.

Time: Computerized accounting has the advantage of increased efficiency and time

management when compared with manual accounting. Computers may more rapidly

perform accounting functions or assessments than manual accounting systems, once data

24
has been entered into the system (Ghasemi, M., Shafeiepour, V., Aslani, M., & Barvayeh,

E. (2011).

Accuracy: Computerized accounting has the advantage of higher accuracy when

compared with manual accounting, according to the College Accounting Coach. The

potential for human error is greater when employees are manually completing accounting

procedures. This may be particularly true when dealing with multiple currencies, since

computerized programs can instantly convert exchange rates, according to "Guide to

Computerizing Your Accounting System" from The Manager's Electronic Resource

Center (Amahalu, N., Abiahu, M. F. C., & Chinyere, O. (2017).

Reliability: The advantages of manual or computerized accounting systems may be equal

when it comes to reliability. Manual accounting can function independently of machines

so that work continues when "the system" isn't working. But with modern backup systems

and increased functionality, the disadvantage of reliability in computerized accounting

may be lessened.

Creativity in Analysis: Although computerized accounting systems are adept at rapidly

computing complex analyses of accounting transactions and reports, the subtlety and

focus of an analysis’ conjecture or hypothesis depends on the person operating the

system. In this view, manual accounting may have an advantage over computerized

accounting systems. Without the nuance and experience of an actual person,

25
computerized accounting systems lose their potential for sophisticated analysis.

Additionally, analysis may be hampered or obstructed by software design.

Reporting: The advantages of computerized accounting include fast, complex reporting.

Computerized systems can produce invoices, purchase orders and other documents more

quickly. Many reports are automatically updated and instantly available.

Staffing: Neither manual nor computerized accounting systems take the advantage when

it comes to staffing. It can be costly to staff qualified accountants to complete manual

accounting processes, but it can also be costly to staff accountants familiar with specific

computerized accounting software and programming.

Cost: When it comes to cost comparison, the advantages of manual accounting systems

are clear. Computerized systems can cost millions of dollars to purchase, implement and

maintain. It may be necessary to purchase updated software with some regularity.

2.8.2 Market Forecasting System Web Portal

A web portal is a specially designed website that brings information from diverse sources,

like emails, online forums and search engines, together in a uniform way. Usually, each

information source gets its dedicated area on the page for displaying information (a

portlet); often, the user can configure which ones to display. Variants of portals include

mashups and intranet "dashboards" for executives and managers. The extent to which
26
content is displayed in a "uniform way" may depend on the intended user and the

intended purpose, as well as the diversity of the content. Very often design emphasis is on

a certain "metaphor" for configuring and customizing the presentation of the content (e.g.,

a dashboard or map) and the chosen implementation framework or code libraries. In

addition, the role of the user in an organization may determine which content can be

added to the portal or deleted from the portal configuration (Seyle, 2014).

A portal may use a search engine's application programming interface (API) to permit

users to search intranet content as opposed to extranet content by restricting which

domains may be searched. Apart from this common search engines feature, web portals

may offer other services such as e-mail, news, stock quotes, information from databases

and even entertainment content. Portals provide a way for enterprises and organizations to

provide a consistent "look and feel" with access control and procedures for multiple

applications and databases, which otherwise would have been different web entities at

various URLs. The features available may be restricted by whether access is by an

authorized and authenticated user (Civil Servant, member) or an anonymous website

visitor.(Seyle, 2014).

The main concept is to present the user with a single Web page that brings together or

aggregates content from a number of other systems or servers. The application server or

architecture performs most of the crucial functions of the application. This application

server is in turn connected to database servers, and may be part of a clustered server

environment. High-capacity portal configurations may include load balancing strategies.

27
For portals that present application functionality to the user, the portal server is in reality

the front piece of a server configuration that includes some connectivity to the application

server. For early Web browsers permitting HTML frameset and iframe elements, diverse

information could be presented without violating the browser same-source security policy

(relied upon to prevent a variety of cross-site security breaches). More recent client-side

technologies rely on JavaScript frameworks and libraries that rely on more recent Web

functionality such as WebSockets and asynchronous callbacks using XML Http Requests

(Donna, 2019).

The server hosting the portal may only be a "pass through" for the user. By use of

portlets, application functionality can be presented in any number of portal pages. For the

most part, this architecture is transparent to the user. In such a design, security and

concurrent user capacity can be important issues, and security designers need to ensure

that only authenticated and authorized users can generate requests to the application

server. If the security design and administration does not ensure adequate authentication

and authorization, then the portal may inadvertently present vulnerabilities to various

types of attacks.

Web portals are sometimes classified as horizontal or vertical. A horizontal portal is used

as a platform to several companies in the same economic sector or to the same type of

manufacturers or distributors. A vertical portal (also known as a "vortal") is a specialized

entry point to a specific market or industry niche, subject area, or interest. Some vertical

portals are known as "vertical information portals" (VIPs). VIPs provide news, editorial
28
content, digital publications, and e-commerce capabilities. In contrast to traditional

vertical portals, VIPs also provide dynamic multimedia applications including social

networking, video posting, and blogging.

2.8.3 Types of Market Forecasting System Web Portal

The following are the various types of web portals and they include;

1. Personal: A personal portal is a Web Page at a Web site on the World Wide Web

or a local HTML home page including JavaScript and perhaps running in a

modified Web browser. A personal portal typically provides personalized

capabilities to its visitors or its local user, providing a pathway to other content. It

may be designed to use distributed applications, different numbers and types of

middleware and hardware to provide services from a number of different sources

and may run on a non-standard local Web server (Susan, 2011). In addition,

business portals can be designed for sharing and collaboration in workplaces. A

further business-driven requirement of portals is that the content be presented on

multiple platforms such as personal computers, laptops, tablet computers, personal

digital assistants (PDAs), cell phones and smartphones. Information, news, and

updates are examples of content that could be delivered through such a portal.

Personal portals can be related to any specific topic such as providing friends

information on a social network or providing links to outside content that may help

others beyond your reach of services. Portals are not limited to simply providing

links. Outside of business intranet user, very often simpler portals become replaced
29
 with richer mashup designs. Within enterprises, early portals were often replaced

by much more powerful "dashboard" designs. Some also have relied on newer

protocols such as some version of RSS aggregation and may or may not involve

some degree of Web harvesting.

2. Government: At the end of the dot-com boom in the 1990s, many governments

had already committed to creating government web portal sites for their citizens.

These included primary portals to the governments as well as portals developed for

specific branches (e.g., a particular government ministry, department or agency), or

for specific sub-audiences (e.g., senior citizens, parents, post-secondary students,

etc.). Notable government web portals include:

 Australia.gov.au for Australia.

 Disability.gov for citizens with disabilities in the United States.

 USA.gov for the United States.

3. Cultural: Cultural portals aggregate digitized cultural collections of galleries,

libraries (see: library portal), archives and museums. This type of portal provides a

point of access to invisible Web cultural content that may not be indexed by

standard search engines. Digitized collections can include scans or digital photos of

books, artworks, photography, journals, newspapers, maps, diaries and letters and

digital files of music, sound recordings, films, and archived websites as well as the

descriptive metadata associated with each type of cultural work (e.g., metadata

provides information about the author, publisher, etc.). These portals are often
30
 based around a specific national or regional grouping of institutions (Michael,

2010). Notable cultural portals include:

DigitalNZ – A cultural portal led by the National Library of New Zealand focused

on New Zealand digital content.

Europeana – A cultural portal for the European Union based in the National

Library of the Netherlands and overseen by the Europeana Foundation.

TUT.by - A commercial cultural portal focused on Belarusian digital content.

4. Corporate: Corporate intranets became common during the 1990s. As intranets

grew in size and complexity, organization webmasters were faced with increasing

content and user management challenges. A consolidated view of company

information was judged insufficient; users wanted personalization and

customization. Webmasters, if skilled enough, were able to offer some capabilities,

but for the most part ended up driving users away from using the intranet. Many

companies began to offer tools to help webmasters manage their data, applications

and information more easily, and by providing different users with personalized

views. Portal solutions can also include workflow management, collaboration

between work groups or branches, and policy-managed content publication. Most

can allow internal and external access to specific corporate information using

secure authentication or single sign-on (Cohn, 2014). With the increase in user-

generated content (blog posts, comments, photos), disparate data silos, and file

formats, information architects and taxonomists will be required to allow users the
31
 ability to tag (classify) the data or content. For example, if a vice-president makes a

blog post, this post could be tagged with her/his name, title, and the subject of the

post. Tagging makes it easier for users of the intranet to find the content they are

interested in. This will ultimately cause a ripple effect where users will also be

generating ad hoc navigation and information flows. Corporate portals also offer

customers and Civil Servants self-service opportunities.

5. Stock: Also known as stock-share portals, stock market portals or stock exchange

portals are Web-based applications that facilitates the process of informing the

share-holders with substantial online data such as the latest price, ask/bids, the

latest News, reports and announcements. Some stock portals use online gateways

through a central depository system (CDS) for the visitors (ram) to buy or sell their

shares or manage their portfolio.

6. Search: Search portals aggregate results from several search engines into one page.

You can find search portals specialized in a product, for example property search

portals. Library search portals are also known as discovery interfaces.

7. Property Search: Property search portals aggregate data about properties for sale

by real estate agents. Notable property search portals in the UK include Nestoria,

Nuroa, OnTheMarket, Rightmove and Zoopla.

8. TENDER: A tender portal is a gateway for government suppliers to bid on

providing goods and services. Tender portals allow users to search, modify, submit,

32
 review and archive data in order to provide a complete online tendering process.

Using online tendering, bidders can do any of the following:

 Receive notification of the tenders.

 Receive tender documents online.

 Fill out the forms online.

 Submit proposals and documents.

 Submit bids online.

9. Hosted: Hosted Web portals gained popularity and a number of companies began

offering them as a hosted service. The hosted portal market fundamentally changed

the composition of portals. In many ways they served simply as a tool for

publishing information instead of the loftier goals of integrating legacy

applications or presenting correlated data from distributed databases. The early

hosted portal companies such as Hyperoffice.com or the now defunct

InternetPortal.com focused on collaboration and scheduling in addition to the

distribution of corporate data. As hosted Web portals have risen in popularity their

feature set has grown to include hosted databases, document management, email,

discussion forums and more. Hosted portals automatically personalize the content

generated from their modules to provide a personalized experience to their users. In

this regard they have remained true to the original goals of the earlier corporate

Web portals. Emerging new classes of Internet portals called Cloud Portals are

showcasing the power of API (Application Programming Interface) rich software

33
 systems leveraging SOA (service-oriented architecture, Web services, and custom

data exchange) to accommodate machine to machine interaction creating a more

fluid user experience for connecting users spanning multiple domains during a

given "session". Cloud portals like Nubifer Cloud Portal show what is possible

using Enterprise Mashup and Web Service integration approaches to building

cloud portals (Susan, 2011).

10. Domain-Specific: A number of portals have come about which are specific to a

particular domain, offering access to related companies and services; a prime

example of this trend would be the growth in property portals that give access to

services such as estate agents, removal firm, and solicitors that offer conveyancing.

Along the same lines, industry-specific news and information portals have

appeared, such as the clinical trials-specific portal (Tatnall, A. (Ed.). (2005)

2.8.4 Database for Market Forecasting System

Using database technology to gather, store and process information about your

customers, suppliers and even competitors can give your business a distinct advantage.

A sophisticated relational database management system can help you store a vast

amount of data which, as it builds up over time, can become increasingly useful and

valuable. For example:

 Historical data can show you business trends

 Sales records can identify valuable customers

34
A good database design is important in ensuring consistent data, elimination of data

redundancy, efficient execution of queries and high performance application. The

outline of the table allows data to be consistent. Implementation of primary keys and

unique constraints ensures consistency in the stored data (Seyle, 2014).

Your gathering, storage and processing of customers' personal data must comply with

data protection legislation, including the requirement not to collect or process excessive

or unnecessary personal data. Under the GDPR, you must ensure the personal data you

are processing is:

 Adequate - sufficient to properly fulfil your stated purpose

 Relevant - has a rational link to that purpose

 Limited to what is necessary - you do not hold more than you need for that

purpose.

Managing information means taking care of it so that it works for us and is useful for

the tasks we perform. By using a DBMS, the information we collect and add to its

database is no longer subject to accidental disorganization. It becomes more accessible

and integrated with the rest of our work. Managing information using a database allows

us to become strategic users of the data we have. We often need to access and re-sort

data for various uses. These may include:

 Creating mailing lists

 Writing management reports

 Generating lists of selected news stories

35
  Identifying various client needs

The processing power of a database allows it to manipulate the data it houses, so it can:

Sort, Match, Link, Aggregate, Skip fields, Calculate, Arrange, etc.

Because of the versatility of databases, we find them powering all sorts of projects. A

database can be linked to:

 A website that is capturing registered users

 A client-tracking application for social service organizations

 A medical record system for a health care facility

 Your personal address book in your email client

 A collection of word-processed documents

 A system that issues airline reservations

2.8.5 Merits of Integrating Databases in Web Applications

Developing a database for any system can help you:

1. Reduce the amount of time you spend managing data.

2. Analyze data in a variety of ways.

3. Promote a disciplined approach to data management.

4. Turn disparate information into a valuable resource.

5. Improve the quality and consistency of information.

Many businesses do not have the time or resources available to gather and process large

quantities of information. This may lead to a lack of information about:

36
How their business is performing, how profitable their product lines are, If customers are

making repeat purchases, etc (Samuel, 2010).

However, the following key benefits can be identified when using databases for web

applications and they include;

1. Self-Describing Nature Of A Database System: A database system is referred to

as self-describing because it not only contains the database itself, but also metadata

which defines and describes the data and relationships between tables in the

database. This information is used by the DBMS software or database users if

needed. This separation of data and information about the data makes a database

system totally different from the traditional file-based system in which the data

definition is part of the application programs (Berg, K. L., Seymour, T., & Goel, R.

(2013).

2. Insulation between Program and Data: In the file-based system, the structure of

the data files is defined in the application programs so if a user wants to change the

structure of a file, all the programs that access that file might need to be changed as

well. On the other hand, in the database approach, the data structure is stored in the

system catalogue and not in the programs. Therefore, one change is all that is

needed to change the structure of a file. This insulation between the programs and

data is also called program-data independence (Rodrigue, 2018).

3. Support for Multiple Views of Data: A database supports multiple views of data.

A view is a subset of the database, which is defined and dedicated for particular
37
 users of the system. Multiple users in the system might have different views of the

system. Each view might contain only the data of interest to a user or group of users

(Rundensteiner, E. A. (1992)

4. Sharing of Data and Multiuser System: Current database systems are designed for

multiple users. That is, they allow many users to access the same database at the

same time. This access is achieved through features called concurrency control

strategies. These strategies ensure that the data accessed are always correct and that

data integrity is maintained. The design of modern multiuser database systems is a

great improvement from those in the past which restricted usage to one person at a

time (Bertino, E., & Sandhu, R. (2005).

5. Control Of Data Redundancy: In the database approach, ideally, each data item is

stored in only one place in the database. In some cases, data redundancy still exists

to improve system performance, but such redundancy is controlled by application

programming and kept to minimum by introducing as little redundancy as possible

when designing the database (Sean, 2010).

6. Data Sharing: The integration of all the data, for an organization, within a database

system has many advantages. First, it allows for data sharing among Civil Servants

and others who have access to the system. Second, it gives users the ability to

generate more information from a given amount of data than would be possible

without the integration (Yu, K., Froese, T., & Grobler, F. (2000).

38
7. Enforcement Of Integrity Constraints: Database management systems must

provide the ability to define and enforce certain constraints to ensure that users enter

valid information and maintain data integrity. A database constraint is a restriction

or rule that dictates what can be entered or edited in a table such as a postal code

using a certain format or adding a valid city in the City field. There are many types

of database constraints. Data type, for example, determines the sort of data permitted

in a field, for example numbers only. Data uniqueness such as the primary key

ensures that no duplicates are entered. Constraints can be simple (field based) or

complex (programming) (Sumathi, S., & Esakkirajan, S. (2007)

8. Restriction Of Unauthorized Access: Not all users of a database system will have

the same accessing privileges. For example, one user might have read-only access

(i.e., the ability to read a file but not make changes), while another might have read

and write privileges, which is the ability to both read and modify a file. For this

reason, a database management system should provide a security subsystem to

create and control different types of user accounts and restrict unauthorized access

(Donna, 2019).

9. Data Independence: Another advantage of a database management system is how it

allows for data independence. In other words, the system data descriptions or data

describing data (metadata) are separated from the application programs. This is

possible because changes to the data structure are handled by the database

39
 management system and are not embedded in the program itself (Sumathi, S., &

Esakkirajan, S. (2007).

10. Transaction Processing: A database management system must include concurrency

control subsystems. This feature ensures that data remains consistent and valid

during transaction processing even if several users update the same information

(Stankovic, J. A., Son, S. H., & Hansson, J. (1999).

11. Provision for Multiple Views Of Data: By its very nature, a DBMS permits many

users to have access to its database either individually or simultaneously. It is not

important for users to be aware of how and where the data they access is stored

(Suárez, E., Lettieri, S., Zwier, M. C., Subramanian, S. R., Chong, L. T., &

Zuckerman, D. M. (2014)

12. Backup And Recovery Facilities: Backup and recovery are methods that allow you

to protect your data from loss. The database system provides a separate process,

from that of a network backup, for backing up and recovering data. If a hard drive

fails and the database stored on the hard drive is not accessible, the only way to

recover the database is from a backup.

If a computer system fails in the middle of a complex update process, the recovery

subsystem is responsible for making sure that the database is restored to its original

state. These are two more benefits of a database management system (Michael,

2010).
40
2.8.6 Roles of a Database Administrator

Database administration defines a technical function that is responsible for physical

database design and for dealing with technical issues such as security enforcement,

database performance, and backup and recovery and often some mixture of these duties

(Alhassan, M. M., & Adjei-Quaye, A. (2017).

A database administrator is a full time manager responsible for maintaining a DBMS and

ensuring accuracy and the integrity of data. Some specific roles of a database

administrator include:

1. Determine what data should go into the database

2. Determine what relationships should exist between different data items

3. Identify who has permission to read the database information (allocate passwords)

4. Specifies who has the authority to update the database.

5. To be involved in the design of the database and make changes if necessary

6. To keep users informed of any changes

7. To maintain the data dictionary

8. To provide training to users

41
2.8.7 Database Query Market Forecasting System

Users interact with database systems through query languages.(Johnson et al, 2002).The

database management system in return interacts with the database by issuing instructions

known as queries to the database. These queries are executed and the appropriate results

are obtained and sent back to the software. These queries are written in what are known

as query languages, and they employ the non-procedural approach of programming. The

query language of a database management system performs the tasks of defining the data

structures that serve as receptacles for the data of the database, and also to allow the

speedy retrieval and modification of data. Accordingly, two components of a query

language can be identified namely: the data definition component and the data

manipulation component. The task of data manipulation are data retrieval and data update

respectively. Data retrieval entails obtaining data stored in the database that satisfies a

certain specification formulated by the user in a query while data update includes data

modification, deletion and insertion.

2.9 Review of Related Literature

The literature below serves as supporting details about the impact of computerized

Market Forecasting System in stores.

In today's business environment, even many smaller businesses have come to rely on

computerized inventory management systems. Certainly, there are plenty of small retail

outlets, manufacturers, and other businesses that still rely on manual means of inventory
42
tracking. Indeed, for some businesses such as convenience stores, shoe stores, or nurseries

the purchase of an electronic inventory tracking system might constitute a wasteful use of

financial resources. But for firms operating in industries that feature high volume

turnover of raw materials and/or finished products, computerized tracking systems have

emerged as a key component of business strategies aimed at increasing productivity and

maintaining competitiveness. Moreover, the recent development of powerful computer

programs capable of addressing a wide variety of record keeping needs including

inventory management in one integrated system have also contributed to the growing

popularity of electronic inventory control options( Eme, O., Uwazuruike, F. O., & Ukpai,

C. U. (2018)

In the late 1990s many businesses were investing heavily in integrated order and

inventory systems designed to keep inventories at a minimum and replenish stock

quickly. But as Eskow noted, business owners have a variety of system integration

options from which to choose, based on their needs and financial liquidity (Financial

Crisis Inquiry Commission. (2011))

A computer is a programmable device that can automatically perform a sequence of

calculations or other operations on data without human aid. It can store, retrieve, and

process data according to internal instructions. Computers are used in government,

industry, nonprofit and nongovernmental organizations, and in the home, but their impact

has been greatest in business and industry. The competitive nature of business has created

demands for continuous advances in computer technology and systems design.

43
Meanwhile, the declining prices of computer systems and their increasing power and

utility has led more and more enterprises to invest in computer systems for an ever

widening range of business functions (Baldwin, C. Y., & Clark, K. B. (2003) Today,

computers are used to process data in all aspects of a business enterprise: product design

and development, manufacturing, inventory control and distribution, quality control, sales

and marketing, service data, accounting, and personnel management. They are also used

in businesses of all sizes and in all industry segments, including manufacturing,

wholesale, retail, services, mining, agriculture, transportation, and communications. A

retail point of sale system typically includes a cash register (which in recent times

comprises a computer, monitor, cash drawer, receipt printer, customer display and a

barcode scanner) and the majority of retail POS systems also include a debit/credit card

reader (Franciska, A. M., & Sahayaselvi, S. (2017). It can also include a convey or belt,

weight scale, integrated credit card processing system, a signature capture device and a

customer pin pad device. More and more POS monitors use touch-screen technology for

ease of use and a computer is built into the monitor chassis for what is referred to as an

all-in-one unit. All-in-one POS units liberate counter space for the retailer. The POS

system software can typically handle myriad customer based functions such as sales,

returns, exchanges, layaways, gift cards, gift registries, customer loyalty programs,

promotions, discounts and much more. POS software can also allow for functions such

as pre-planned promotional sales, manufacturer coupon validation, foreign currency

handling and multiple payment types (Cohanier, B. (2014).

44
The history of computing is as old as mankind. In the past counting and other arithmetic

operations were affected by the use of different parts of the human body such as fingers

and ties. The earliest known, calculating device, abacus may have been in use as early as

5,000 BC. Calculating was effected by sliding beads along the groves from one side of

the board to the other (Woods, M., & Woods, M. B. (2000)

In 1617, John Napier invested logarithms and a device called Napier Bones. All these

calculating device were invested to ease the calculating process and to generate more

accurate results which in turn will ensure the keeping of accurate records applicable for a

good control system.

A definition that is commonly quoted is that produced by the American Institute of

Certified and Public Accountant (AICPA) in 1941 defines accounting as the art of

recording, classifying and summarizing, in a significant manner and in terms of money

transactions and events which are in part least, of a financial character, and interpreting

the result therefore, another definition by the American Accounting principle board in

1970 (APE NO:4) defines accounting as a service activity. It’s function is to provide

possible quantitative information, primary financial in nature, about economic entities

that is intended to be useful in making economic decisions, in making reasoned choices

among alternative course of action.

As man became more sophisticated with the resultant increase in the volume of records

and data to be processed as well as the need for faster processing and more accurate

results, it became very important to incorporate machines such as computers in the

45
processing of data or information in both the public and private sectors of the economy

(Caruso, L. (2018).

Computers can also process several programs at same time known as multi programming,

and allow several users to access the system con-currently on a multi – use basis. In a

competitive environment the business that is quick to regard to change will have a distinct

advantage over competitors and in recent times and now, business operations take place

in a tense natural and international area, an extremely volatile environment largely

consisting of random events beyond direct control and in which competition is critical,

profit margins are generally narrow and taxation is high (Henderson, B. D. (1989)

Unfortunately, most stores in the nation especially those located in a very competitive

environment have not been computerized and as a result, there have cases here and

therefore, pilfering, defrauding and total management and of course, subsequent folding

up of those stores.

For the fact that ROBAN STORES is not to be counted out; and for it to over come such

formidable obstacles to the accomplishments of it’s business objectives, this case study

becomes inevitable as to provide management with the ever needing more “intelligent” by

way of information reports so that it may run the business as effectively as possible and

effort such adverse factors. We are beyond no reasonable doubt believing that computers

are installed in ROBAN STORES with suitable peripherals and programs; a great deal of

information is potentially available for management decision making. More so, the basic

computing system’s is purpose of serving some routine such as keeping customers

46
addresses or recording stock, or producing weekly – pay – slips will be satisfied (Swift,

R. S. (2001).

Meigs et al, (1998) Computerized accounting system also known as a Market Forecasting

System, is a system that uses computers to input, process, store and output accounting

information in form of financial reports. He adds that accounting system records all

transactions that routinely deal with events that affect the financial position and

performance of an entity.

Marivic (2009) described a computerized accounting system also known as Market

Forecasting System as a method or scheme by which financial information on business

transactions are recorded, organized, summarized, analyzed, interpreted and

communicated to stakeholders through the use of computers and computer based systems

such as accounting packages. He emphasized that it’s a mechanized process of facilitating

financial information inflows as well as the automation of accounting tasks such as

database recording and report generation. Marivic adds that keeping accurate accounting

records is a vital part of any organization. Apart from helping it to keep its float

financially and legal, it is a requirement of funding bodies or donors.

McBride (2000) explained that computerized packages can quickly generate all types of

reports needed by management for instance budget analysis and variance analysis. Data

processing and analysis are faster and more accurate which meets the managers need for

accurate and timely information for decision making.

47
Meigs (1986) stresses that there is a risk of improper human intervention with the

computer programs and computer files. Employees in the stores may temper with the

computer programs and computer based records for the purpose of deliberately falsifying

accounting information. This may result into distortion of information that would

essential be for decision making.

According to Wahab (2003), another threat and limitation of computerized system is the

computer virus. Where a computer virus is a computer code (program) specially designed

to damage or cause irregular behavior in other programs on the computer. The adverse

effect is that it may lead to breakdown of the hardware thus leading to loss of valuable

information (for instance in financial institutions information such as customer’s

accounts, previous financial report, information pertaining loans advanced among others)

already saved on the computer.

Lewis (1999) also stated that computerization saves time on transaction hence leading to

quality of financial reporting for instance timely, accurate and reliable information can be

generated.

48
 CHAPTER THREE

METHODOLOGY AND SYSTEM ANALYSIS

3.1 Methodology Adopted

The structured system analysis and design methodology (SSADM) was adopted for the

analysis, design and implementation of this system. Structured systems analysis and design

methodology (SSADM) is a set of standards for systems analysis and application design. It

uses a formal methodical approach to the analysis and design of information systems.

SSADM follows the waterfall life cycle model starting from the feasibility study to the

physical design stage of development. One of the main features of SSADM is the intensive

user involvement in the requirements analysis stage. The users are made to sign off each stage

as they are completed assuring that requirements are met. The users are provided with clear,

easily understandable documentation consisting of various diagrammatic representations of

the system. SSADM breaks up a development project into stages, modules, steps and tasks.

The first and foremost model developed in SSADM is the data model. It is a part of

requirements gathering and consists of well defined stages, steps and products. The techniques

used in SSADM are logical data modeling, data flow modeling and entity behavior modeling.

i. Logical Data Modeling: This involves the process of identifying, modeling and

documenting data as a part of system requirements gathering. The data are classified

further into entities and relationships.

ii. Data Flow Modeling: This involves tracking the data flow in an information system. It
clearly analyzes the processes, data stores, external entities and data movement.
49
 iii. Entity Behavior Modeling: This involves identifying and documenting the events
influencing each entity and the sequence in which these events happen.

3.2 Analysis of the Existing System

The analysis of the existing system comprises the following;

i. Input Analysis: The input of layout of the existing system comprises user intervention

such as; Adding items to Cart, opening account and login into system.

ii. Process Analysis: The customer is add items needed to cart, each it comprises the item

amount, stock available, and stock sold. The e-billing process takes the data from user

input, the processed inputted data was automatically generated, thereby generated a bill

for payment process.

A payment system is any system used to settle financial transactions through the transfer

of monetary value. This includes the institutions, instruments, people, rules, procedures,

standards, and technologies that make its exchange possible. A common type of payment

system is called an operational network that links bank accounts and provides for

monetary exchange using bank deposits. Some payment systems also include credit

mechanisms, which are essentially a different aspect of payment.

a) Output Analysis: The output from the system designed is generated from the system

inputs. These reports can also be presented as hard copy.

The operations of the Automated Intelligent System for Online Market Forecasts Using

Statistical Model were analyzed, and some drawbacks were detected which led to the

initiation of the new Automated Intelligent System for Online Market Forecasts Using
50
Statistical Model. In the old system, the method is tedious and it gives room for loss of vital

information, duplication of information etc, which makes it difficult to process the report

effectively or efficiently.

3.2.1 Dataflow of the Existing System

AUTOMATED INTELLIGENT SYSTEM

FOR ONLINE MARKET FORECASTS

Input Analysis Output Analysis

Process
Fill Item Analysis Produce Result
Request Form

Process Request
Opening Account Generate Report

Process New
Login to System Account

Validate Login
Details

Figure 3.2.1: Dataflow of the Existing System

51
3.2.2 Disadvantages of the Existing System

Some of the problems identified in the present system include:

1. The speed of processing data manually is low and prone to errors.

2. The current process is stressful to end-users

3. Things done manually were very uncomfortable.

3.2.3 Weakness of the Existing System

The weaknesses of the existing system are as follows depending on the method used;

1. Cash Weakness: Most people do not carry much cash on top. Increasingly, people use

credit or debit cards and do not carry many bills. If you only receive cash, you may end up

losing a lot of customers.

2. Credit and Debit Cards Weakness: Credit Cards can add another level of difficulty to

bookkeeping and accepting credit cards can be an added monthly expense in most cases,

Credit cards do come with risks such as charge backs and fraud, and Refunds on credit

cards are not immediate.

3. Mobile Payments Weakness: Problems with the updates. A simply failed update can

break the whole system and prevent you from continuing to charge normally. So be very

careful if you update the application you use to charge and make sure it is compatible with

your phone before installing it.

52
3.3 Feasibility Study

This assumes that the proposed project has been identified as a result of an exercise such as

strategic planning and sets out to evaluate the various technical, organizational, financial and

business options available. The aim is to establish the whether the direction and requirements

of the project are feasible. The aim is to evaluate the feasibility of the proposal, involving an

analysis of the problem and determination of the best solution; usually a range of potential

solutions are presented.

3.3.1 Technical Feasibility

There is availability of software, hardware and technical man power for the development and

running of the new system. Hence the system is technically feasible as the requirement can be

met without stress and much financial input. The software and hardware requirements include

an Integrated Development Environment for web based applications, a standard PC for

running this application, a local server and an up to date web browser for testing. As a

programmer, the researcher can provide these requirements with ease and as such, this project

is technically feasible.

3.3.2 Operational Feasibility

The new system is operationally feasible as it will be used and managed by users who are at

least intermediate computer operators and it doesn’t require an expert knowledge of the

system before it can be implemented. Also, the system is designed to be user friendly and

efficient; therefore the project is operationally feasible.

53
3.3.3 Economic Feasibility

The proposed system is cheap to implement and less expensive to maintain, the economic

challenge might emerge in the purchase of some hardware (such as, a computer system) and

software (such web browser and WAMP Server) requirements which can be easily taken care

of, no much requirements are needed for this system and such the system is economically

feasible. Besides, the proposed could be marketed for other financial gains to similar drug

information services.

3.4 Analysis of the Proposed System

An overview of the proposed system flow chat has a relationship between an object to another

just like the entity. Relationship diagram, the object relationship pair can be graphically

represented by a diagram called entity relationship diagram (Entity Relationship Diagram). It

is mainly used in database applications but now it is more commonly used in data design. The

primary purpose of ERD is to represent the relationship between data object.

54
3.4.1 Data Flow Diagram of the Proposed System

This is a data flowchart of the proposed system as shown in figure 3.2.

Sends Success / Failure

ADMIN TABLE ADMIN

Found / Not Found Login

LOGIN ACCOUNT
Found / Not Found Login

Success / Failure

MAREKT TABLE END-USER

Success / Failure
Sends

Registration Details

REGISTER

Figure 3.2: Data Flow Diagram of the Proposed System

3.4.2 Advantages of the Proposed System

The following are the advantages of the proposed Automated Intelligent System for Online

Market Forecasts Using Statistical Model;

i. Low labour costs: Since online payments are usually automatic, they have lower labour
costs than manual payment methods, such as cheque, money order, cash, and so on.
ii. Convenience for online sales: Online payment methods allow conveniently selling
goods and services online.

55
iii. Automatic: Online payments can be automatic, which can be convenient for you and
your customers.
iv. Fast transaction speed: Online transactions quickly provide feedback to you and your
customers.
v. Low risk of theft: After processing delays, online payments generally go straight into
your bank account, so they have a low risk of theft.
3.4.3 Justification of the Proposed System

In every organization (ROBAN STORES) encounter numerous problems, which include

keeping goods, maintaining, checking and having goods account records for goods in stock.

The relevance of the study will:

 Inform and guide customers and the general public on the kind of services offered by

ROBAN STORES as regards their commercial operations, goods and stock available for

sale and the benefit and preferential treatments given to the customers who buy goods in

bulk or in large quantities.

 To incorporate computer into the daily operations of the store with reference to mainly

it’s accounting system, as well as its stock control system and its day to day commercial

operations. With introduction and application of computer into the operations of the

STORE the organization will be able to improve dramatically on its daily information and

accounting system.

3.5 Functional Requirements

The following figure 3.4 shows the various modules involved in the system and available to

users who have limited access and to the Admin who have full access to the system.
56
 3.5.1 Use Case Diagram Of The Admin / User Privileges

Update

Deactivate
Account

Activate

Figure 3.3: Use Case diagram of the

ADMIN

Add to Cart

Input
END-

Open Account

Figure 3.4: Use Case diagram of the User

57
3.6 Data Requirements

The following are the data requirements of new and existing users in the system. New users

are required to create an account by providing some necessary information such as:

a) Email Address: The user's email address is required during registration and subsequent

login on the system.

b) Password: The user is required to enter a secured password or pin during registration

and subsequent login on the system

c) User Name: The user is required to enter a nickname which he/she will be addressed as

subsequently for security reasons.

d) Passport: This field contains the photograph or picture of the account holder or system

user.

e) Address: This field contains the address of the system user.

58
3.7 High Level Model of the Proposed System

The high level model of the proposed system is illustrated below;

AUTOMATED INTELLIGENT SYSTEM FOR

ONLINE MARKET FORECASTS USING
STATISTICAL MODEL

HOME Admin END-USER (Client)

Update Record

Open Account
Deactivate
Account
Add Forecasted
Activate Price
Account

Respond View Receipt

Make Payment
for Bill

System Logout

Figure 3.4: High Level Model of the Proposed System

59
 CHAPTER FOUR

SYSTEM DESIGN AND IMPLEMENTATION

4.1 Objectives of the Design

The following are the objectives of the proposed Automated Intelligent System for Online

Market Forecasts Using Statistical Model design will;

i. Provide software interface for monitoring and control of online markets

ii. Automate customer, product, and supplier management on the system

iii. Enables business owners predict future business trends.

iv. Improve existing statistical model for intelligently forecasting online market trends.

4.2 System Specifications

4.2.1 Math Specifications

Linear Regression (LR): Linear regression analysis is used to predict the value of a

variable based on the value of another variable. The variable you want to predict is called

the dependent variable. The variable you are using to predict the other variable's value is

called the independent variable.

This form of analysis estimates the coefficients of the linear equation, involving one or more

independent variables that best predict the value of the dependent variable. Linear regression

fits a straight line or surface that minimizes the discrepancies between predicted and actual

output values.

60
Mathematical Formulation: A linear regression line equation is written in the form of: Y = a

+ bX

where X is the independent variable and plotted along the x-axis

Y is the dependent variable and plotted along the y-axis

The slope of the line is b, and a is the intercept (the value of y when x = 0).

Linear Regression Formula

Linear regression shows the linear relationship between two variables. The equation of linear

regression is similar to the slope formula.

Now, here we need to find the value of the slope of the line, b, plotted in scatter plot and the

intercept, a.

Linear Regression Line

The most popular method to fit a regression line in the XY plot is the method of least-squares.

This process determines the best-fitting line for the noted data by reducing the sum of the

squares of the vertical deviations from each data point to the line. If a point rests on the fitted

line accurately, then its perpendicular deviation is 0. Because the variations are first squared,

then added, their positive and negative values will not be cancelled.
61
Linear regression determines the straight line, called the least-squares regression line (LSRL).

Suppose Y is a dependent variable, and X is an independent variable, then the population

regression line is given by;

Y = B0+B1X

Where

B0 is a constant

B1 is the regression coefficient

If a random sample of observations is given, then the regression line is expressed by;

ŷ = b0 + b1x

where b0 is a constant, b1 is the regression coefficient, x is the independent variable, and ŷ is

the predicted value of the dependent variable.

62
Regression Coefficient

In the linear regression line, we have seen the equation is given by;

Y = B0+B1X

Where

B0 is a constant

B1 is the regression coefficient

Now, to find the value of the regression coefficient.

B1 = b1 = Σ [ (xi – x)(yi – y) ] / Σ [ (xi – x)2]

Where xi and yi are the observed data sets.

And x and y are the mean value.

4.2.2Programming Module Specification

Creating a program for an automated intelligent system for online market forecast using a

linear regression model involves several key module specifications. Here's an outline of the

modules for this system:

1. Data Collection Module:

 Description: This module gathers historical market data from various online sources.

63
 Specifications: Interface with APIs or web scraping tools to collect market data, Store

collected data in a structured database for further analysis.

2. Data Preprocessing Module:

 Description: This module prepares the collected data for analysis by cleaning and

transforming it.

 Specifications: Handle missing or incomplete data points, Normalize or standardize data

to ensure uniformity. It convert categorical variables into numerical values if applicable.

3. Linear Regression Model Module:

 Description: This module builds and trains the linear regression model for market

forecasting.

 Specifications: Implement the linear regression algorithm (you can use libraries like

scikit-learn in Python). Train the model using the training data, Evaluate the model's

performance using metrics like Mean Squared Error.

4. Automated Forecasting Module: Description: This module uses the trained model to make

predictions for future market trends.

 Specifications:Integrate the trained model into the system, Provide a mechanism for users

to input relevant parameters for market prediction. It generate forecasts based on user

input and the trained model.

5. User Interface Module:

 Description: This module provides a user-friendly interface for interacting with the

system.
64
 Specifications:Develop a web-based or desktop application interface, Include input fields

for users to enter parameters such as market segment, time period, etc. It display the

forecasted market trends graphically.

4.2.3 Input and Output Format

Input Data:

 The system accepts input data in structured formats.

 Users can input real-time sales data. The data can be organized in a tabular format that

consists of time period and prices.

65
 Proposed System Inputs

Output Format:

 The primary output of the system is the market forecast, which predicts the market

metric of interest for the specified future time period. This forecast can be a single

numerical value or a time series of predicted values, depending on the granularity of

the forecast.

66
 Proposed System output

4.3 Database Specification and Design

The Computerized Market Forecasting System database contains four (4) tables which are

Category Table, Inventory Table, Inventory Record Table, and Login Table:

67
Table 4.3.1: Category Table

S/N Field Name Field Type Field Length

1 Id Integer 30

2 Category Varchar 100

Table 4.3.2: Inventory Table

S/N Field Name Field Type Field Length

1 Id Integer 30

2 description Varchar 1000

3 Image Varchar 100

4 Stock Varchar 30

5 Stockshown Varchar 100

6 Price Varchar 30

7 category Varchar 1000

8 tdate Varchar 30

68
Table 4.3.3: Inventory Record Table

S/N Field Name Field Type Field Length

1 Id Integer 30

2 amount Varchar 30

3 numberofstock Varchar 30

4 stockid Varchar 30

5 tdate Varchar 50

Table 4.3.4: Login Table

S/N Field Name Field Type Field Length

1 Id Integer 30

2 user Varchar 50

3 pass Varchar 50

69
4.2.4 Algorithm

LR Algorithm: The goal of LR is to find the best-fitting line by estimating the coefficients

(B0 and B1) that minimizes the sum of squared errors(residuals) between the observed(Y) and

predicted (ŷ) values.

Step1. Input data:

 Collect the dataset with pairs of X and Y values

Step2. Calculate Means:

 Calculate the mean of X(Ẍ) and the mean of Y(ȳ).

Step3. Calculate slope(B1):

B1= ∑((Xi−Ẍ)* (Yi-Ȳ))

∑((Xi−Ẍ)^2)

Step4. Calculate intercept(B0):

 Calculate B0 using the formular:

 B0 = Ȳ - B1 * Ẍ

Step5. Make prediction:

 Use the calculated B0 and B1 to predict Y for the new X values:

Ŷ = B0 + B1 * X

70
Step6. Evaluate the model:

 Use evaluation metrics like mean squared error to assess the model’s accuracy.

4.3Data Dictionary

The data dictionary table contains the list of field and their description used in the database

table structure designation.

Table 4.5: Proposed System Data Dictionary

S/N Field Name Field Description

1. id Unique Identification
2. category Item Category
3. description Item Description
4. Image User Photo
5. Stock Stock Items
6. Stockshown Available Stock
7. Price Item price
8. category Item category
9. tdate Transaction Date
10. amount Item Category
11. numberofstock Number of Stock Sold
12. stockid Stock Identification
13. user Username
14. pass Password

71
4.4 System Flowchart
Start

Enter Cart ID

Validate Cart ID

Input Item
Number

Display
Forecasted Result

Answer security
question B

N Display
Are answers Error
message
YE
Pay Bill

Save

Stop

Figure 4.4: System Operation Flowchart

72
4.5 System Implementation

To ensure a standardized object oriented program in its entire ramification, HTML, CSS,

JAVASCRIPT, PHP and MYSQL Database was used in the development of Automated

Intelligent System for Online Market Forecasts Using Statistical Model. These entire

programs are used to ensure effective program. The motive behind the use of the language is

its compatibility with several Operating Systems. It is object oriented and combines the

feature of hypertext Preprocessor (PHP) and JavaScript platform thereby making it to run on

any Operating System. It is secured in that it does not cause harm to user’s system and access

to information is restricted. The language is simple and easy to learn.

4.5.1 System Requirements

4.5.1.1 Hardware Requirements

The hardware requirements for the proposed system are as follows:

 Server: A dedicated server with sufficient processing power and memory to handle data

processing and real-time integration tasks.

 Storage: Adequate storage capacity to accommodate historical data and model files.

73
4.5.1.2 Software Requirements

The software requirements encompass the following:

 Operating System: The system is compatible with various operating systems, including

Windows, Linux, and macOS.

 A web server software, such as Apache, Nginx, is necessary to handle HTTP requests and

serve web applications.

 Machine learning libraries and frameworks like scikit-learn are indispensable for

prediction.

 Web Browser: Users need a modern web browser to access the user interface.

4.5.2 Program Development

Program development is a pivotal phase in the creation of Automated intelligent system for

online market forecast using statistical method, encompassing a series of vital activities that

bring the software and algorithms to life. It begins with meticulous system design, where

architects delineate the system's architecture, database structure, user interface, and data flow,

charting the course for development. Concurrently, machine learning algorithms and models

are crafted, trained, and fine-tuned to analyze data and generate market predictions.

74
User interface (UI) designers craft the system, translating it into wireframes and prototypes to

ensure a user-friendly and intuitive experience. Front-end developers then embark on building

the UI using web development technologies like HTML, CSS, JavaScript, and modern

frameworks such as React or Angular. This ensures that the interface is responsive and cross-

browser compatible.

4.5.3 System Testing

System testing is a critical phase in the development of an automated intelligent system for

online market forecasting. It ensures that the system functions as intended, providing accurate

and reliable market predictions. Comprehensive testing is essential to identify and rectify any

issues before the system is deployed into a production environment. Here's a detailed

overview of the system testing process for this scenario:

75
 Test Type Test Description Method Test
Result
Unit Test Individual components and functions
Testing
Test modules such as data preprocessing, Used test cases to validated passed
regression model implementation and functionality of each unit
prediction generation. independently
Integration Verify That Each Modules Work
Testing Together Seamlessly.
Test the interactions between modules, Conducted tests that examined data passed
especially data flow between consistency and integrity during
preprocessing, regression model, and transitions between modules
output generation.
Performa Evaluate The System's Responsiveness,
nce Stability, And Resource Usage Under
Testing Various Conditions
Measured system response times, resource Used tools like Apache JMeter to passed
utilization, and throughput under different simulate various user loads and
loads and scenarios. analyze the system's performance
metrics.
Regression To Ensure That New Code Changes Do
Testing Not Adversely Affect Existing
Functionalities.
Re-run previous test cases to validate that Automated test suites are run every passed
existing features still work after new time a change is made to the system's
features or bug fixes are implemented. codebase.
User To Validate The System From The End-
Acceptance Users' Perspective And Ensure It Meets
Testing The Business Requirements.
Evaluated the system's functionality, Involved real users who assess the passed
usability, and overall user satisfaction. system through predefined scenarios,
ensuring it aligns with their
expectations and needs.
Security To Identify Vulnerabilities And Ensure
Testing That User Data And The System Itself
Are Protected Against Unauthorized
Access And Attacks.
Test for common security vulnerabilities Used manual and automated testing passed
such as SQL injection, cross-site scripting techniques, including vulnerability
(XSS), and data breaches. scanning, and code analysis tools.
Model To Assess The Predictive Performance
Evaluation Of The Linear Regression Model.
/Validation
Evaluated the model's accuracy, precision Utilized techniques like cross- passed
and other relevant metrics using test validation, where the dataset is
datasets. divided into multiple subsets, and the
model is trained and evaluated
multiple times to ensure robustness.
76
4.5.4 Training

Training of the machine learning models is a vital component of the system implementation.

Historical data is used to train the LR model, which allows them to make accurate sales

predictions. Regular model re-training is scheduled tomake sure the models adapt to changing

market conditions.

4.5.5 Documentation

System documentation is essential as it provides a clear roadmap of the system's design, data

flow, and functionalities. It ensures understanding, facilitates collaboration among team

members, enables efficient maintenance, aids in troubleshooting, and supports informed

decision-making, ensuring the system operates effectively and accurately predicts

online market trends.

4.5.6 System Conversion

System conversion involves transitioning from an existing system to a new one. In the context

of implementing an automated intelligent system for online market forecasting using a linear

regression model, several crucial steps ensure a successful transition.

Changeover Procedures:

 Analysis: Thoroughly assess the existing system's strengths and weaknesses.

 Requirements: Define precise requirements for the new system, involving experts and
stakeholders.
 Data Preparation: Collect and preprocess historical market data for regression analysis.
77
 Model Development: Create and validate the linear regression model, ensuring accuracy.
 Integration: Integrate the model into the system architecture and conduct extensive
testing.
 User Training: Provide user training and create intuitive interfaces for seamless
interaction.
 Implementation: Execute the changeover plan, monitor the system, and resolve issues
promptly.
Recommended Procedure for Automated System:

 Project Kickoff: Assemble a diverse team and define clear project goals, scope, and
timeline.
 Data Preparation: Cleanse and transform historical market data, selecting relevant
features.
 Model Development: Implement and optimize the linear regression model, validating its
accuracy.
 Integration: Integrate the model into an automation framework, enabling real-time data
updates.
 User Interface: Design a user-friendly interface allowing input parameters and market
forecast visualization.
 Deployment and Maintenance: Deploy the system securely, establish monitoring
protocols, and provide ongoing support.
 Documentation: Create comprehensive documentation covering system functionalities
and troubleshooting guidelines.
By following these steps, businesses can seamlessly transition to an automated intelligent

system, empowering data-driven decision-making and enhancing their competitive edge in the

online market.

78
 CHAPTER FIVE

SUMMARY, CONCLUSION, AND RECOMMENDATION

5.1 Summary

Market forecasting is the process of making predictions of the future based on past and present

data and analysis of trends. Computerization of the store can remove wastage, guarantee quick

service at service points of vital importance to the public and improve productivity. Such

computerization effort often costs for less than the money and time it will save both the public

and the organization. Computers will remain an integral part of life; this is as a result of

increasing number of areas where they have become indispensible. Worthy of note also is the

fact that business decision making relies heavily on market competition, this makes market

forecasting very important in business planning.

The motivation revealed that statistical models have been useful in solving a variety of tasks.

However, in online marketing forecasts this is yet to be fully realized. Thus, there is need to

improve on existing models or invent new ones that can help online markets predict or

forecast best market scenarios and avoid huge financial losses.

The methodology adopted in this study is the structured system analysis and design

methodology (SSADM) which is a technical approach for analyzing and designing an

application or system by applying object throughout the software development process. The

programming language used is HTML, CSS, JAVASCRIPT, PHP, SQL and JQUERY. The

reason why web programming languages was used is because, it is platform independent and
79
it is a web based application. The proposed system will help organization to Predict

achievable sales revenue, efficiently allocate resources, Plan for future growth etc. This

project will be of benefit to Enterprises, Shopping Malls/Supermarkets and many large

companies. The expected result is an electronic billing system that will process customer’s

selected items in a shopping mall or supermarket, and the system will be able to forecast

product prices base on the previous sales using linear regression model.

5.2 Conclusion

The development of an automated intelligent system for online market forecasting using a

linear regression model represents a pivotal milestone in the intersection of technology and

business strategy. This sophisticated system, rooted in the principles of data science and

machine learning, offers businesses a powerful tool to navigate the complexities of the online

market landscape.

At its core, the success of this system hinges upon the quality and depth of the data it

processes. Accurate and comprehensive datasets serve as the lifeblood, enabling the linear

regression model to discern patterns, identify trends, and make informed predictions. The

meticulous process of data preprocessing, involving cleaning, feature selection, and

normalization, ensures that the model operates on reliable information, laying the foundation

for precise forecasting.

80
The choice of a linear regression model, while a seemingly straightforward one, is

underpinned by its interpretability and versatility. Its ability to distill complex market

dynamics into comprehensible insights is invaluable. Striking a delicate balance between

model simplicity and accuracy is an art; a model that is too simplistic might overlook crucial

nuances, while an overly complex one might succumb to overfitting. The iterative process of

model evaluation and optimization refines the system, enhancing its predictive capabilities.

A core feature of this intelligent system lies in its adaptability. The online market is a dynamic

arena, subject to rapid shifts and evolving trends. Hence, the system’s ability to adapt to real-

time data, adjust its algorithms, and recalibrate predictions is paramount. Continuous

monitoring ensures that the model remains relevant and reliable, providing businesses with

timely and actionable insights.

Furthermore, interdisciplinary collaboration emerges as a cornerstone. The synergy between

domain experts, data scientists, and software engineers enriches the system’s understanding of

market intricacies. Domain knowledge, coupled with data-driven insights, refines the model,

making it a true reflection of market realities.

User experience and usability are paramount in the system’s effectiveness. A well-designed

interface, coupled with intuitive visualizations, translates complex data into actionable

intelligence for end-users. Clarity and simplicity empower stakeholders to grasp the insights

swiftly, fostering informed decision-making.

81
5.3 Recommendation

In the final analysis, the development and deployment of an automated intelligent system for

online market forecasting using a linear regression model demand a strategic approach and a

commitment to continuous enhancement. To ensure sustained success, here are the concluding

recommendations:

1. Continuous Refinement:

Iterative Development: Embrace an iterative approach to development. Regularly evaluate the

system's performance and refine algorithms and data inputs for enhanced accuracy.

Adaptability: Stay nimble and adapt the system to evolving market trends. Integrate new data

sources and features to capture changing consumer behaviors and preferences.

2. Ethical and Responsible AI:

Bias Mitigation: Continuously monitor and mitigate biases within the data and algorithms.

Implement fairness measures to ensure unbiased predictions.

Transparency: Maintain transparency in your processes. Clearly communicate how predictions

are made, ensuring users understand the system's limitations.

3. User-Centric Focus:

User Feedback: Actively seek user feedback and incorporate user suggestions for system

improvements. Regular user engagement ensures the system remains aligned with user needs.

User Training: Provide training and resources to users, enabling them to interpret system

outputs effectively. Educated users make better strategic decisions.

82
4. Cross-Disciplinary Collaboration:

Interdisciplinary Teams: Foster collaboration between data scientists, market experts, and

technology specialists. Diverse perspectives enrich the system's understanding and predictive

capabilities.

Knowledge Sharing: Encourage a culture of knowledge sharing within your team. Share

insights and best practices to enhance the collective expertise.

5. Scalability and Security:

Scalable Architecture: Design the system with scalability in mind. Ensure it can handle

increased data volumes and user interactions without compromising performance.

Robust Security: Prioritize data security. Implement robust encryption, access controls, and

regular security audits to safeguard sensitive information.

6. Continuous Learning:

Stay Updated: Remain abreast of the latest advancements in AI, machine learning, and market

analysis. Regularly update the system to incorporate cutting-edge techniques.

In essence, the journey of developing an automated intelligent system for online market

forecasting using a linear regression model is not a one-time endeavor but an ongoing

commitment to excellence. By adhering to these recommendations, the system can evolve,

adapt, and consistently deliver valuable, data-driven insights, positioning your organization at

the forefront of the ever-changing online market landscape.

83
 REFERENCES
"More Consumers Using Tablets to Holiday Shop [STUDY]". Mashable. December 8, 2011.

Adeoti, O., &Osotimehin, K. (2012). Adoption of point of sale terminals in Nigeria:

Assessment of consumers’ level of satisfaction. Research Journal of Finance and
Accounting, 3(1), 1-6
.
Agrawal, M., & Bansal, A. (2018). A REVIEW STUDY ON ELECTRONIC PAYMENT
SYSTEM. Prestige International Journal of Management and Research, 10(5), 5-14.

Ahn, H., & Lee, S. (2021). Development and validation of an automated stock trading system
using machine learning algorithms. Expert Systems with Applications, 166, 114124.

Bonsoni (2021), "Research shows word of mouth drives online sales". Retrieved from
Bonsoni.com on Retrieved 2012-01-19.

Bunn, D. W., & Day, M. R. (2013). Forecasting intraday arrivals at a call center. Management
Science, 59(8), 1809-1825. doi: 10.1287/mnsc.1120.168

Chen, C., Li, Q., & Da, Y. (2017). A new online forecasting approach using hybrid statistical
learning algorithms for stock markets. IEEE Transactions on Cybernetics, 47(3), 570-
583. doi: 10.1109/TCYB.2016.2537978

Chong, E. P., & Han, W. (2019). Intelligent trading systems: A comprehensive review.
Information Fusion, 46, 215-240.

CIO (2021), "CIO Magazine, Enterprise Resource Planning Center, On-line ERP information
resources". Retrieved from www.cio.com/forums/erp/ (accessed on 27th July, 2021)

Cohn, M. (2014). "Zoho Revamps Online Accounting Software". Accounting Today. Retrieved
29 January 2014.

CRMCommunity (2021), "CRM Community. Web community portal for customer relationship
management". Retrieved from www.CRMCommunity.com. (accessed on 27th July,
2021)

CRMMagazine (2021), "CRM Magazine, Leading CRM industry publication". Retrieved from
www.CRMMagazine.com (accessed on 27th July, 2021)

84
Cvsonline (2021), "Certificate Verification System". Retrieved from
http://www.cvsonline.net/index.php?p=about (accessed on 27th June, 2021)

Draper, N. R., & Smith, H. (2014). Applied regression analysis.

John Wiley & Sons.

Donna, O. (2019). "What is horizontal portal? definition and meaning".

BusinessDictionary.com. Retrieved 8 August 2019.

Fraenkel, J. &Wallen, C. (2010). The Challenges of conducting educational research in

Colleges of Education. In A. O. Ajayi (Ed). Institittionalization of research and
development, Ibadan: Outprints.

Geoplace (2021), "Business Geographics Magazine. Portal site for GIS systems information
and suppliers". Retrieved from www.bg.geoplace.com (accessed on 27th July, 2021)

Hair, J. F., Black, W. C., Babin, B. J., & Anderson, R. E. (2019). Multivariate data analysis.
Pearson.

Hyndman, R. J., & Athanasopoulos, G. (2018). Forecasting: principles and practice. OTexts.

ISO/IEC/IEEE (2010) ISO/IEC/IEEE International Standard—Systems and Software

Engineering—Vocabulary 24765(E). Verification 5: Product, Service, or System
Complies with a Regulation, Requirement, Specification, or Imposed Condition.

Michael, S. (2010). CPA Technology Advisor. "Building Strategy: How Workflow,

Document Management and Portals Work Together".

Montgomery, D. C., Peck, E. A., & Vining, G. G. (2012). Introduction to linearregression

analysis. John Wiley & Sons.

PCI Security Standards Council. "PCI Data Storage Do’s and Don’ts". Retrieved 24 March
2013.

Privacyalliance (2021), "Privacy Alliance. An alliance of over 100 leading businesses and
trade associations dedicated to protecting privacy on-line". Retrieved from
www.privacyalliance.org (accessed on 27th July, 2021)

85
Raymond McLeod,Jr. 1995, Sistem Informasi Manajemen, Jakarta : PT.Prenhalindo
Rodrigue, J. (2018). American Institute of CPAs. "The Rage Surrounding Client
Portals".
Rouse, M. (2006) Definition of Certification.
https://whatis.techtarget.com/definition/certification

Roy, S., & Sinha, I. (2014). Determinants of customers’ acceptance of electronic payment
system in Indian banking sector–a study. International Journal of Scientific and
Engineering Research, 5(1), 177-187.

Samuel, D. (2010). Journal of Accountancy. "Client Portals: A Secure Alternative to E-

Mail".
Schapranow, S. (2014). A logical approach to research proposal Development. In A. O.
Ajayi (ed). Institutionalization of research and development. Ibadan: Oduprints.

Sean, O. (2010). CPA Technology Advisor. "Building Strategy: How Workflow, Document
Management and Portals Work Together".

Seyle, T. (2014). "Expand Your Solo or Small Firm Practice Using Client Portals" (PDF).
Law Practise Today. Retrieved 29 January 2014.

Supply-chain (2021), "Supply Chain Council. Portal site for supply chain management
information, conferences, and solutions". Retrieved from www.supply-chain.org
(accessed on 27th July, 2021)

Susan, L. (2011). "What is vertical portal? definition and meaning".

BusinessDictionary.com. Retrieved 8 August 2011.

The heralding website, September 2014. http://www.theheraldng.com/e-commerce-

development-nigeria/
Tran, E. (1999), "Verification". Retrieved from
https://users.ece.cmu.edu/~koopman/des_s99/verification/ (accessed on 27th June,
2021)
Walker, John (2007-11-22). "RPS Exclusive: Gabe Newell Interview". Rock, Paper,
Shotgun. Retrieved 2013-06-28.

Yaqub, J. O., Bello, H. T., Adenuga, I. A., &Ogundeji, M. O. (2013). The cashless policy in
Nigeria: prospects and challenges. International Journal of Humanities and Social
Science, 3(3), 200-212.
86
 Appendix A: Source Code

Appendix B: Questionnaire
Questionnaire Sample: Thank you for participating in our research study. Your
responses are valuable in understanding user perspectives on our Automated
Intelligent System for Online Market Forecast. Please answer the following
questions honestly and to the best of your knowledge.

Section 1: General Information

• Age: [ ] years
• Gender: [ ] Male [ ] Female [ ] Non-binary [ ] Prefer not to say
• Occupation: [ ] Student [ ] Professional [ ] Entrepreneur [ ] Other (please specify:
________________)
• How often do you engage in online shopping? [ ] Daily [ ] Weekly [ ] Monthly [ ]
Rarely [ ] Never

Section 2: System Usage

• Have you used automated systems for market forecast before? [ ] Yes [ ] No
• On a scale from 1 to 5, how would you rate your experience with our Automated
Intelligent System? (1 being very poor, 5 being excellent) [ ] 1 [ ] 2 [ ] 3 [ ] 4 [ ] 5
• What features did you find most useful in the system?
[ ]Accurate Predictions
[ ]User-Friendly Interface
[ ] Quick Response Time
[ ] Detailed Insights
[ ] Other (please specify: ________________)

Section 3: Linear Regression Model

• Were the market predictions made by the system accurate in your opinion? [ ]
Yes [ ] No [ ] Not Sure
• What improvements, if any, would you suggest for enhancing the accuracy of the
market predictions?

87
Secton 4: User Experience
• Was the system interface easy to navigate? [ ] Yes [ ] No [ ] Somewhat
• Do you have any suggestions for improving the system's user interface or user
experience?

Secton 5: General Feedback

• What do you think are the potential real-world applications of this system in the
online market industry?
• Any additional comments or feedback you would like to provide about the
Automated Intelligent System for Online Market Forecast?

Thank you for taking the time to complete this questionnaire. Your input is
invaluable and greatly appreciated.

88