‘

DEPARTMENT OF MBA & EMBA PROGRAMS

Data analysis on demand and forecasting of Swiss’s products

OPM501: Operations Management

Section: 2
Summer – 2022

Prepared for
Dr. A. K. M. Masud
Adjunct Faculty

Prepared by

● Ishrak Ahmed 2022-1-95-140

● Shajidur Rahman Chowdhury 2022-2-95-040
● Samira Taznin Chowdhury 2021-1-95-005

Date of Submission: December 11, 2022

December 11, 2022
Dr. A. K. M. Masud
Adjunct Faculty
East West University
Aftabnagar, Dhaka – 1212, Bangladesh

Subject: Submission of report on “Data analysis on demand and forecasting of Swiss

bakery products”

Dear Sir,

As a requirement for completing the OPM501 course under the MBA program of East West
University, we would like to submit our report titled “Data analysis on demand and
forecasting of Swiss bakery products”.

We sincerely hope that this report fulfills the objectives and requirements of the course studies
and that it finds your acceptance. We have attempted to finish the report with the essential data
and recommended proposition in as compact and comprehensive a manner as possible.

We are grateful for your guidance and kind cooperation at every step of our endeavor in this
report. We shall remain deeply grateful if you kindly take some pen to review the report and
evaluate our performance.

Sincerely yours,

Ishrak Ahmed 2022-1-95-140

Shajidur Rahman Chowdhury 2022-2-95-040

Samira Taznin Chowdhury 2021-1-95-005

Page | 2
Acknowledgment

We would like to express our utmost gratitude and wholehearted appreciation to the almighty
Allah, who aided us with his strength and gave us wisdom, and patience to complete and present
this report.

First of all, we would like to thank our honorable faculty, Dr. A. K. M. Masud for providing us
with the opportunity to observe and analyze such an interesting topic and for his supervision,
relentless guidance, and invaluable advice whenever needed.

We would also like to acknowledge all those seniors, and sites who helped us during the
completion of this report.

Finally, we are pleased to complete the report on the given subject properly and authentically.

Page | 3
Executive Summary

The purpose of this report is to analyze the sales data and forecast the sales of Swiss Bakery. In
this study, the financial data is analyzed through quantitative methods and interpreted
accordingly. The report is constructed based on one year (January 2021 - December 2021) sales
data of Swiss bakery. To fulfill the study, the data has been collected from one of the operation
managers of Swiss Bakery.

The report has been prepared in different chapters divided in three chapters. The first chapter
focuses on the introduction of the report. The second chapter focuses on the data analysis of
Swiss Product and lastly the final chapter consists of the conclusion part.

According to the analysis of the study, Most and least appropriate forecasting method for Swiss
products has been reflected. The identified problem has been listed in detail in chapter three of
this report.

Page | 4
Contents
CHAPTER 1: INTRODUCTION 6

1.1 An Overview of Forecasting 6

1.2 Objectives 8

1.3 Scope & Methodology 8

1.4 Limitations 9

CHAPTER 2: DATA ANALYSIS 9

2.1 Moving Average: 9

2.2 Weighted Moving Average: 10

2.3 Exponential Smoothing: 10

2.4 Linear Regressions: 11

CHAPTER 3: CONCLUSION 13

Page | 5
CHAPTER 1: INTRODUCTION
1.1 An Overview of Forecasting
Forecasting usually refers to the prediction of the future. Forecasting is a technique that uses
historical data as inputs to make informed estimates that are predictive in determining the
direction of future trends. In other words, forecasting means projecting past sales demand into
the future. Businesses use forecasting to determine how to manage their budgets or plan for
anticipated expenses for the future. Business uses forecasting for production, raw material
procurement, human resource, finance etc. Previous data are important for forecasting because it
helps to make accurate forecasts. There are two types of forecasting:

i. Qualitative (Judgmental)

ii. Quantitative (Time series analysis)

Qualitative Forecasting: Qualitative forecasting is an estimation methodology that uses expert

judgment, rather than numerical analysis. This forecast depends on the highly experienced
employee or consultants to make a forecast. There are several types of qualitative forecasting
methods:

1. Grass Roots: Customer or end user of product knows best its demand.
2. Market Research: Market survey and interviews of the consumers.
3. Panel Consensus: Panel of people from a variety of positions from management to
workmen, open meeting. People who know more about the marketplace. Will have a
open meeting
4. Executive Judgment: Higher level strategic decision to introduce new product line, new
marketing area. No opinions are taken, only higher-level people will decide by
discussion.
5. Historical Analogy: Analysis of contemporary products. i.e., CD and CD Player, Stereo
VCR and Digital video disk player.
6. Delphi Method: Choose the experts of all the departments to participate. There should be
a variety of knowledgeable people in different areas. Through a questionnaire (or
E-mail), obtain forecasts (and any premises or qualifications for the forecasts) from all
participants. Summarize the results and redistribute them to the participants along with

Page | 6
 appropriate new questions. Summarize again, refining forecasts and conditions, and again
develop new questions. Repeat Step 4 if necessary. Distribute the final results to all
participants.

Quantitative Method: Quantitative forecasting is a data-based mathematical process that sales

teams use to understand performance and predict future revenue based on historical data
and patterns. Forecasting results give businesses the ability to make informed decisions on
strategies and processes to ensure continuous success. There are several types of quantitative
forecasting methods:

1. Simple-moving average:

Ft = 𝐴 𝑡−1
+𝐴𝑡−2+𝐴𝑡−3+…+𝐴𝑡−𝑛
𝑛

2. Weighted Moving Average:

Ft = W1At-1 + W2At-2 + W3At-3 + ... + WnAt-n

𝑛
∑ 𝑊𝑖 = 1
𝑖=1

3. Exponential Smoothing

Ft = Ft-1 + α (At-1 - Ft-1)

• Premise--The most recent observations might have the highest predictive value.
• Therefore, we should give more weight to the more recent time periods when forecasting

4. Simple Linear Regression Model:

Yt = a + bx

Page | 7
 • b is similar to the slope. However, since it is calculated with the variability of the data in
mind, its formulation is not as straight-forward as our usual notion of slope

Calculating a and b

● Forecast Errors

1.2 Objectives
▪ To analyze the data of Swiss Bakery and forecast their upcoming sales.

1.3 Scope & Methodology

The present study has been carried out to analyze the sales of Swiss Products. This study has
been based on data from primary sources. The relevant data and information were collected
through one of the operation managers of Swiss Bakery. In this study, different data of concerned
companies have been analyzed during the period January 2021- December 2021. For evaluating
the performance, these data have been analyzed through quantitative methods.

Page | 8
1.4 Limitations
▪ It is a part of the coursework, not independent research.
This study was conducted over a period of 4 weeks. A longer period for analysis might have put extra
light on this study.

CHAPTER 2: DATA ANALYSIS

Swiss Bakery:
Month Sales (Vanilla Sales (Special
Cake) Mocha Cake)
January 2021 80 80
February 2021 95 90
March 2021 100 45
April 2021 115 55
May 2021 60 115
June 2021 130 200
July 2021 140 140
August 2021 150 70
September 2021 160 100
October 2021 70 65
November 2021 85 92
December 2021 105 110

Source: Data compiled from one of operation managers of Swiss Bakery

2.1 Moving Average:

Vanilla Cake Special Mocha Cake
Month Sales 3 period Sales 3 Period
moving Error moving Error
average average
January 2021 80 80
February 2021 95 90
March 2021 100 45
April 2021 115 91.66 23.33 55 71.67 16.67
May 2021 60 103.33 43.33 115 63.33 51.67
June 2021 130 91.66 38.34 200 71.67 128.33
July 2021 140 101.67 38.33 140 123.33 16.67
August 2021 150 110 40 70 151.67 81.67
September 2021 160 140 20 100 136.67 36.67
October 2021 70 150 80 65 103.33 38.33
November 2021 85 126.67 41.67 92 78.33 13.67
December 2021 105 105 0 110 85.67 24.33

Page | 9
 Sum Error 325 408.01

MAD 36.11 45.33

2.2 Weighted Moving Average:

Let the Weights are t-1= 0.6; t-2 =0.3; t-3= 0.1

Vanilla Cake Special Mocha Cake

Month Sales Error Sales WMA Error
WMA
January 2021 80 80
February 2021 95 90
March 2021 100 45
April 2021 115 96.5 18.5 55 72 17
May 2021 60 108.5 48.5 115 55.5 59.5
June 2021 130 80.5 49.5 200 90 110
July 2021 140 107.5 32.5 140 160 20
August 2021 150 129 21 70 155.5 85.5
September 2021 160 145 15 100 104 4
October 2021 70 155 85 65 95 30
November 2021 85 105 20 92 76 16
December 2021 105 88 17 110 84.7 25.3
Sum Error 307 367.3
MAD 34.11 40.81

2.3 Exponential Smoothing:

Smoothing constant equal to 0.20
Vanilla Cake Special Mocha Cake
Month Sales ES Error Sales ES Error

January 2021 80 80(assume) 0 80 80(assume) 0

February 2021 95 80 15 90 80 10
March 2021 100 81 19 45 82 37
April 2021 115 84.8 30.2 55 74.6 19.6
May 2021 60 90.84 30.84 115 70.68 44.32
June 2021 130 84.67 45.33 200 79.54 120.46
July 2021 140 93.76 46.24 140 103.62 36.38
August 2021 150 103.008 46.99 70 110.896 40.896

Page | 10
 September 2021 160 112.41 47.59 100 102.72 2.72
October 2021 70 121.928 51.928 65 102.18 37.18
November 2021 85 111.54 26.54 92 94.74 2.74
December 2021 105 106.23 1.23 110 94.20 15.8
Sum Error 360.89 367.096

MAD 30.07 30.59

Note:

2.4 Linear Regressions:

Vanilla Cake Special Mocha Cake

Month (X) Sales Forecast Error Sales Forecast Error
(Y1) LR (Y2) LR
January 2021 80 98.271 18.27 80 86.86 6.86
February 2021 95 99.949 4.95 90 88.68 1.32
March 2021 100 101.627 1.63 45 90.49 45.49
April 2021 115 103.305 11.70 55 92.30 37.30
May 2021 60 104.983 44.98 115 94.12 20.89
June 2021 130 106.661 23.34 200 95.93 104.07
July 2021 140 108.339 31.66 140 97.74 42.26
August 2021 150 110.017 39.98 70 99.55 29.55
September 2021 160 111.695 48.31 100 101.37 1.37
October 2021 70 113.373 43.37 65 103.18 38.18
November 2021 85 115.051 30.05 92 104.99 12.99
December 2021 105 116.729 11.73 110 106.81 3.19
Sum Error 309.97 343.47
MAD 25.83 28.623

Page | 11
 Month (X) X^2 Y1 X*Y1 Y2 X*Y2
1 1 80 80 80 80
2 4 95 190 90 180
3 9 100 300 45 135
4 16 115 460 55 220
5 25 60 300 115 575
6 36 130 780 200 1200
7 49 140 980 140 980
8 64 150 1200 70 560
9 81 160 1440 100 900
10 100 70 700 65 650
11 121 85 935 92 1012
12 144 105 1260 110 1320
6.5(Average) 650 107.5(Average) 8625 96.83(Average) 7812

Product 1: Vanilla Cake

∑𝑥𝑦1−𝑛 (𝑦1)(𝑥)
𝑏= 2
2
∑𝑥 −𝑛(𝑥)

8625−12*107.5*6.5
= 2 = 1.678
650−12*(6.5)

a =𝑦 − 𝑏𝑥 = 107.5- (1.678) *(6.5) = 96.593

Product 2: Special Mocha Cake

∑𝑥𝑦2−𝑛 (𝑦2)(𝑥)
𝑏= 2
2
∑𝑥 −𝑛(𝑥)

7812−12*96.83*6.5
= 2 = 1.813
650−12*(6.5)

a =𝑦 − 𝑏𝑥 = 96.83-(1.813) *(6.5) = 85.05

Page | 12
Result Analysis:

Vanilla Cake Special Mocha Cake

Foreca Forecast/ Forecast/ Forecast/W Forecast/ Forecast/ Forecast/ Forecast/W

st/ LR MA ES MA LR MA ES MA

MAD 25.83 36.11 30.07 34.11 28.62 45.33 30.59 40.81

Moving average methodology displays the highest MAD in Vanilla Cake. This indicates that the
moving average method is the least suitable/acceptable for predicting the sales of vanilla cakes.
Moving average methodology displays the highest MAD in Special Mocha Cake. Therefore, the
moving average method is the least suitable/acceptable method to predict Special Mocha Cake
sales.

CHAPTER 3: CONCLUSION
In this report, we have tried to analyze the sales data and forecasted the sales of Swiss Bakery.
The forecasting was covered under four quantitative methods: Moving average, weighted
moving average, exponential smoothing and linear regression. In each method we calculated
error, forecasted sales, sum error and MAD which helped us to figure out the appropriate forecast
method for the subject. For both the products Linear Regression will be the most appropriate
method.

Page | 13