Case Study-3 (Forecasting)

Dr. Md.
Ahsan Akhtar Hasin Professor, BUET
Application of Proper Forecasting Technique

in Juice Production: A Case Study
Rakesh Kumar & Dalgobind Mahto
Green Hills Business and Engineering College, India
Abstract
Every organization that produces products evaluate their performance at certain intervals to
keep the pace with the market. Forecasts are evaluated to improve accuracy in planning
outcomes. The purpose of this study is to observe whether the forecast errors are within the
reasonable limit of expectations or whether these errors are irrationally large and require an
improvement in the statistical models and process of producing these forecasts. Time series
modeling techniques like – Simple Moving Average, Exponential Smoothing and Least
Square methods are used for the study and their performance evaluated in terms of some
forecasting error measurement technique, such as Mean Average Deviation (MAD), Mean
Squared Error (MSE).
Introduction
Modern production activities are becoming more complex technologically, the basic inputs
are becoming expensive and there are lot of restrictions on them. The planning of the
production activities is, therefore, essential to put the resources for best use. Planning is a
fundamental activity of management. Forecasting forms the basis of planning and it enables
the organization to respond more quickly and accurately to market changes. It plays a crucial
role in the development of plans for the future. It is essential for the organizations to know for
what level of activities the company is planning before investments in inputs i.e. man,
machine and materials. It uses many mathematical techniques for forecasting and subsequent
production and resource planning. It requires systematic analysis of past and present
circumstances. It is essentially a technique of anticipation and prediction. Before making an
investment decision, questions may arise like:
• What should be the size of the production order, purchase order and stock?
• What should be the capital cost required for the work?
• What should be the capacity of the plant, or, how many and what type of machines are
required ?
• How much labor is required?
The answers to the above questions depend upon the forecast for the future level of
operations and related resources. The success of a business greatly depends upon the efficient
forecasting and accurately preparing for future events. It should be no surprise that forecasts
are not always accurate – they are essentially about predicting the future with incomplete
information, often invalid information for various socio-economic reasons. Nevertheless,
forecast inaccuracies, particularly consistent underestimation of revenues and budget
surpluses generally draws intense criticism. Forecast accuracy has been a matter of concern
and subject of review. In general, the reasons for inaccuracies may fall into the following
categories:
Dr. Md. Ahsan Akhtar Hasin Professor, BUET
 Technical issues, such as data inaccuracy,

 Improper forecasting methodology
 Incompetent manpower in judgment and lack of skill in analysis techniques
 Effects of fiscal limitations, etc.
Forecasting manpower generally review and improve data and models on an ongoing basis.
But they often fail to relate ongoing social and economic changes, turbulence, public policy
change, government budgetary and taxation laws, etc.
Case Objective
The objectives of this case study are, however, limited to identifying results obtained from
widely used forecasting techniques, and judge their effectiveness using some error
measurement techniques.
The main emphasis of this work is to compare the various forecasting techniques prevalent in
the industries based on the data obtained from a juice producing factory. In this manuscript an
attempt has been made to forecast juice production by using the Simple Moving Average
Method, Exponential Smoothing and Least Squares Method. The aim is to evaluate the
performances in terms of –
• Mean Absolute Deviation (MAD)

• Mean Squared Error (MSE)
• Mean Absolute Percentage Error (MAPE) and
• Finally, to compare the findings and decide the suitability among the methods MAD, MSE
and MAPE.
Methodology
This study was carried out on the basis of juice production data collected for the period 2008 to 2018
as shown in the Table 1.
The company is located in the middle of the state of Gujarat. It is completely locally owned, enlisted in
Mumbai stock-exchange. The company was established in year 2000. However, systematic
mathematical forecasting techniques are being used from year 2008. Prior to that, only judgmental
qualitative techniques were used.
Table 1: Actual Production data
Sl. No. Year Production

(million liters)
1 2008 16.6
2 2009 19.3
3 2010 20.8
4 2011 23.8
5 2012 26.5
6 2013 29.0
7 2014 31.1
8 2015 33.4
9 2016 36.4
10 2017 38.9
11 2018 40.7
It is essential to select the right forecasting method in order to succeed in subsequent

production and other relevant planning, such as transportation planning, warehouse planning,
market planning, distribution planning, packaging planning, etc.
a) Simple Moving Average Method
When demand for a product is neither growing nor declining rapidly and if it does not have
seasonal characteristics, a moving average can be useful in removing the random fluctuations
for forecasting.
Equal weighting is given to each of the values used in the moving average calculation,
whereas it is reasonable to suppose that the most recent data is more relevant to current
conditions. This is a major drawback of Simple Moving Average method. Thus, it may create
inaccuracies in demand estimation, leading to invalid planning.
b) Exponential Smoothing Method
In the previous forecasting method, the major drawback is the need to continually carry a
large amount of historical data. As each new piece of data is added in these methods, the
oldest observation is dropped, and the new forecast is calculated. The reason this is called
exponential smoothing is that each increment in the past.
The value of smoothing constants α varies from 0 to 1. This smoothing constant works as
weightage on (or importance of) either the previous forecast or previous actual demand.
Wrong selection of α value leads to inaccuracies. It not easy to select the right value of α
either. It requires high level of experience, judgmental power, observation power and in-
depth knowledge on ever changing economic, social and business parameters. Failure to do
so leads to inaccurate forecasting and subsequent planning.
c) Least Squares Method
Theoretically speaking, in case of linear increase of demand, this is the most accurate
technique. Failure to judge linearity is a major problem. In such a situation, it may create
wrong results.
Evaluating the Forecast Accuracy

There are many ways to measure forecast accuracy. Some of these measures are the mean
absolute forecast error, called the MAD (Mean Absolute Deviation), the Mean Absolute
Percentage Error (MAPE) and the Mean Square Error (MSE). This error estimate helps in
monitoring erratic demand observations. In addition, they also help to determine when the
forecasting method is no longer tracking actual demand and it need to be reset. For this
tracking signals are used to indicate any positive or negative bias in the forecast. The mean
absolute deviation (MAD) is also important because of its simplicity and usefulness in
obtaining tracking signals. MAD is the average error in the forecasts, using absolute values. It
is valuable because MAD, like the standard deviation, measures the dispersion of some
observed value from some expected value. The only difference is that like standard deviation,
the errors are not squared. Standard error a square root of a function, it is often more
convenient to use the function itself. This is called the mean square error (MSE) or variance.
The mathematical formulas may be used while evaluating data. The following interesting
results were obtained (Table 2):
Table 2. Accuracy found in Juice production
Measures Simple Moving Exponential Least Squares

of Average Method Smoothing Method
accuracy
MAPE 15.74% 31.83% 0.95%
MAD 4.96 10.08 0.25
MSE 24.57 120.60 0.09
The data show that in case of moving average method, value of MAPE, MAD and MSE are
15.74%, 4.95 and 24.57 respectively. For Simple Exponential Method, value of MAPE,
MAD and MSE are 31.83%, 10.08 and 120.60 respectively. Similarly, in case of Least
Squares Method value of MAPE, MAD and MSE are 0.95%, 0.25 and 0.09.
By comparing the performance of the methods, it was found that Least Squares method have
the least value of MAPE (15.74%), MAD (0.25) and MSE (0.09) and hence the results
produced by the least square method have less error and more accuracy than the other
methods. Thus, it was concluded that Regression Analysis (or, Least Squares Method) is the
most suitable technique for Juice production and thus, will be used in the following 10 years.
After that, the same analysis would be done again to see if the conclusion still remain valid,
or change of forecasting method is required. Remember that in future, the Least Squares
Method may not remain the most suitable one, depending on market pattern, consumer
behavior, substitutes available, level of competition, government taxation policy, national
economic growth, purchasing power of people, etc.
Q1) According to your judgment, what kind the demand patterns do your business or
products follow ? Out of the above 3 forecasting methods (discussed in this case study),
which one should be more suitable to your company ? Justify.
Q2) What social, economic and business parameters affect your business the most ? Identify
3 most important parameters, which affect your business.

Case Study-3 (Forecasting)

Uploaded by

Copyright:

Available Formats

Case Study-3 (Forecasting)

Uploaded by

Document Information

Original Title

Copyright

Available Formats

Share this document

Share or Embed Document

Sharing Options

Did you find this document useful?

Is this content inappropriate?

Copyright:

Available Formats

Case Study-3 (Forecasting)

Uploaded by

Copyright:

Available Formats

Dr. Md.

Ahsan Akhtar Hasin Professor, BUET

Application of Proper Forecasting Technique

 Technical issues, such as data inaccuracy,

• Mean Absolute Deviation (MAD)

Table 1: Actual Production data

Sl. No. Year Production

It is essential to select the right forecasting method in order to succeed in subsequent

a) Simple Moving Average Method

b) Exponential Smoothing Method

c) Least Squares Method

Evaluating the Forecast Accuracy

Table 2. Accuracy found in Juice production

Measures Simple Moving Exponential Least Squares

You might also like