Vietnam National University of HCMC

International University
School of Computer Science and Engineering

Course Name: Decision

Support System
Course ID: IT145IU
Semester 1, 2021-2022

Lecturer: Dr. Nguyen Van Sinh

Email: nvsinh@hcmiu.edu.vn
Lecturer Information
l Lecturer & Lab section:
l Lecturer: Dr. Nguyen Van Sinh
l Lab tutor: Msc. Nguyen Quang Phu
l Office: A1.610
l Website: https://it.hcmiu.edu.vn
l Email: nvsinh@hcmiu.edu.vn
nqphu@hcmiu.edu.vn

2
Description
l Introduce the decision support system (DSS), an interactive
computer-based system (or subsystem) intended to help decision
makers.
l DSS simulate cognitive decision-making functions of humans
based on AI methods including the area of knowledges:
l Expert systems,
l Data mining,
l Machine learning,
l Connectionism,
l Logical reasoning,
l DSS refers to an academic field of research that involves designing
and studying DSS in their context of using
l Support skills for student to design and implement an application
for decision maker

3
Learning outcome
l Understand the goals and different forms of decision
support, and gain knowledge of the practical issues of
implementation
l Examine systems based on statistical and logical
approaches to decision making that include statistical
prediction, rule-based systems, case-based reasoning,
neural networks, fuzzy logic, etc.
l Obtain an overview of the various computerized decision
support techniques together with a detailed assessment of
successful and unsuccessful applications developed
l Examine the actual and potential impact of the technology
together with the challenges associated with this kind of
application
l Have knowledge and understanding the basics of DSS,
tools and techniques to develop an application for
supporting decision maker
4
Learning outcome
After successful completion of the course
students should be able to:
l Articulate the role of decision support
systems and expert systems in organizations
l Apply decision theory and other
management science techniques to analyze
problems
l Formulate and use analytical models for
organizational problem solving
l Design and develop an application for
decision support systems and expert systems

5
Requirements
l This is one of the advanced courses; it has a fast pace and
requires much effort spending outside of class time
l Students are expected to study (self-study), review and
combine knowledges in data processing, AI and machine
learning web application development to propose method
and build application in practice.
l Students are expected (required) to attend all class
sections on time and prepared things (very important!)
l Students have to finish their assignments on time.
l If you cannot complete an assignment, contact the
instructor/lab tutor (before the deadline)
l Tests are to be taken at day and time scheduled. DO NOT
copy from another student.
l The proposed topics are covered in expert systems,
diagnosis applications, recommendation systems, smart
management applications, DSS-Apps in any context and
fields.
6
Requirements
Grades will be based on:
l A midterm exam and a final exam
l Assignments include papers review
l Read a paper from the literature
l Write report on paper
l Give oral presentation
l Lab sections and a group project,
l Small groups
l Design and implement DSS for problem of your topic
l Written report
l Oral presentation
 Reading
Textbooks:
1. Ffraim Turban, Ramesh Sharda, Dursun Delen, Jay E. Aronson, Ting-Peng
Liang and David King Decision Support and Business Intelligence
Systems, Ninth Edition, 2011.
2. Ramesh Sharda, Dursun Delen, Efraim Turban - Analytics, Data Science,
& Artificial Intelligence Systems for Decision Support 11th Edition 2019.
3. Daniel J. Power, Ciara Heavin, Decision Support, Analytics, and Business
Intelligence, 3rd Edition, Business Expert Press, 2017.

Referent books:
1. Efraim Turban, Ramesh Sharda, Dursun Delen - Business Intelligence and
Analytics - Systems for Decision Support 2014
2. Diego Galar Pascual - Artificial Intelligence Tools - Decision Support
Systems in Condition Monitoring and DIagnosis 2015
3. Ephraim Turban and Jay Aronson, Decision Support Systems and
Intelligent Systems, Prentice-Hall, 2005
8
Activities
l Lectures: 15 sessions (3 teaching periods
for each), starting from 06/9/2021.
l Lab section: 08 sessions (4 teaching
periods for each), one month after
l Marking:
l Midterm Exam: 25%
l Attendance + Quiz: 10%
l Lab + Project + Assignment: 30%
l Final Exam: 35%

9
Policies
l Attend all lectures, come to class on time
l If in the online class, students are required
to open camera through all lecture time
l If copy program, source code, report from
others → minus 50% of the final grade of
the course
l Absence greater than 20% → you are not
allow taking the final exam
l The quiz will be examined randomly

10
Lectures
l The lecture should be prepared in advance
l It will be uploaded on the blackboard after
presenting on the class
l The exercises will be provided at the end of
each lecture
l Textbooks and referent books are
introduced and shown on the internet
l The related articles are introduced to
research

11
Agenda
Week Section (Handout) Reading
01 L00. Introduction to the course T1.C1; T2.C1
L01. Decision Support System and Business Intelligence
02 L02. Decision Making, System, Modeling and Support T1.C2; T2.C3

03 L03. Decision support systems Concepts, Methodologies and T1.C3; T2.C3

Technologies
04 L04. Modeling and analysis T1.C4; T2.C5
05 L05. Data Mining, Business Intelligence T1.C5; T2.C4
06 L06. Artificial Neural Network and Data Mining T1.C6; T2.C6
07 L07. Text and Web Mining T1.C7; T2.C7
08 L08. Data Warehousing T1.C8
09 L09. Business Performance Management T1.C9
10 L10. Collaborative Computer-Supported Technology and Group T1.C10; T2.C11
Support System
11 L11. Knowledge management T1.C11; T2.C12
12 L12. Artificial intelligent & Expert systems T1.C12; R2.C4
13 L13. Advanced Intelligent Systems T1.C13; T2.C8
14 L14. Management Support System: Emerging Trends and Impacts T1.C14

12
Lab sections
l Software:
l IDE: choose the best one for web-app
development
l DBMS: MySQL or any
l Other frameworks: option to do project
l Working:
l 8 sections
l Finish all required exercises for each lab
l Attend all lab-sections to get advices on the
homework and assignment
l Work hard on your exercises and assignment
topics
l Group project presentation
13
Assignments
l Working in group (2 or 3 students/group)
l Two types of topic:
l Selected topics are provided by lecturer
l Your pre-thesis/thesis topics
l Work at home and in the lab sections
l WHAT ARE WE LOOKING FOR?
l A demo program
l Report document
l Implement various database, functions
with multiple input data, out put is a
best decision of the context
l Present project in the last lab section

14
Projects
l Students must submit a brief proposal when the project
topic is determined, before the first lab section.
l A short conversation or a document not exceeding one
page will suffice (Introduction, purpose, main
functions, how can implement and how they work?)
l Contact the Instructor/Lab tutor if you anticipate
difficulty in finding a project topic. The highest grades
will go to projects that can be applied in practice and to
projects developed independently.
l Each student is required to make a brief presentation (5-
10 minutes) at the last class meeting.
l The coding does not have to be absolutely finished by
that time, but there should at least be a prototype that
conveys the code’s useful functions.
Research topics
Ø An expert system for medical diagnosis
Ø A smart application for medical service
Ø A recommendation system for customers
Ø A support system for course registration
Ø A decision support system for IT recruitment
process
Ø A system to support job finding
Ø A marketing decision model
Ø Your proposal ?

16
Q&A

Thank for your attention!

17