Operations

Management
Topic 2 – Forecasting

UiTM Shah Alam

Lecturer: Dr. JURI SAEDON
T1-A18-13C

5/20/2019
Faculty of Mechanical Engineering,
NY- MEM 575: Courtesy of Mc University
Graw Hill and Technology MARA 1
Pearson-Prentice Hall
 Learning outcomes

At the end of this lesson students should be able to :

1. Discuss the overview of forecasting techniques
2. Compare and contrast qualitative and quantitative approaches to
forecasting
3. Apply the naive, moving averages, weighted moving averages and
exponential smoothing methods.
4. Compute and analyze three measures of forecast accuracy; MAD,
MSE and MAPE

5/20/2019
Faculty of Mechanical
NY- MEMEngineering,
575: Courtesy of University Technology
Mc Graw Hill and MARA
Pearson-Prentice
2
Hall
 What is Forecasting?
1. Process of predicting a
future event Hmm…. you are
going to get an A for
2. Underlying basis of this subject. But!!!

all business decisions

 Production
 Inventory
 Personnel
 Facilities

5/20/2019
Faculty of Mechanical Engineering,
NY- MEM 575: Courtesy of Mc University
Graw Hill and Technology MARA
3
Pearson-Prentice Hall
 Forecasting Time Horizons
1. Short-range forecast
 Up to 1 year, generally less than 3 months
 Purchasing, job scheduling, workforce levels, job
assignments, production levels
2. Medium-range forecast
 3 months to 3 years
 Sales and production planning, budgeting
3. Long-range forecast
 3+ years
 New product planning, facility location, research and
development

5/20/2019
Faculty of Mechanical Engineering,
NY- MEM 575: Courtesy of Mc University
Graw Hill and Technology MARA
4
Pearson-Prentice Hall
 Seven Steps in Forecasting
1. Determine the use of the forecast
2. Select the items to be forecasted
3. Determine the time horizon of the forecast
4. Select the forecasting model(s)
5. Gather the data
6. Make the forecast
7. Validate and implement results

5/20/2019
Faculty of Mechanical Engineering,
NY- MEM 575: Courtesy of Mc University
Graw Hill and Technology MARA
5
Pearson-Prentice Hall
 Types of Forecasts
1. Economic forecasts
 Address business cycle – inflation rate, money supply,
housing starts, etc.
2. Technological forecasts
 Predict rate of technological progress
 Impacts development of new products
3. Demand forecasts
 Predict sales of existing products and services

5/20/2019
Faculty of Mechanical Engineering,
NY- MEM 575: Courtesy of Mc University
Graw Hill and Technology MARA
6
Pearson-Prentice Hall
 Strategic Importance of Forecasting

1. Human Resources – Hiring, training, laying off

workers
2. Capacity – Capacity shortages can result in
undependable delivery, loss of customers, loss of
market share
3. Supply Chain Management – Good supplier
relations and price advantages

5/20/2019
Faculty of Mechanical Engineering,
NY- MEM 575: Courtesy of Mc University
Graw Hill and Technology MARA
7
Pearson-Prentice Hall
 The Realities!

1. Forecasts are seldom perfect

2. Most techniques assume an underlying stability in
the system
3. Product family and aggregated forecasts are more
accurate than individual product forecasts

5/20/2019
Faculty of Mechanical Engineering,
NY- MEM 575: Courtesy of Mc University
Graw Hill and Technology MARA
8
Pearson-Prentice Hall
 Forecasting Methods
Generally there are two types of forecasting
methods; Qualitative and Quantitative Methods

1. Qualitative methods are based on:

 judgment
 opinion
 past experience
 best guesses

2. Quantitative methods are based on:

 mathematical methods
 two traditional types; time series and regression

5/20/2019
Faculty of Mechanical Engineering,
NY- MEM 575: Courtesy of Mc University
Graw Hill and Technology MARA
9
Pearson-Prentice Hall
 Forecasting Approaches
Qualitative Methods
 Used when situation is vague and little
data exist
 New products
 New technology
 Involves intuition, experience
 e.g., forecasting sales on Internet

5/20/2019
Faculty of Mechanical Engineering,
NY- MEM 575: Courtesy of Mc University
Graw Hill and Technology MARA
10
Pearson-Prentice Hall
 Forecasting Approaches
Quantitative Methods
 Used when situation is ‘stable’ and historical
data exist
 Existing products
 Current technology
 Involves mathematical techniques
 e.g., forecasting sales of color televisions

5/20/2019
Faculty of Mechanical Engineering,
NY- MEM 575: Courtesy of Mc University
Graw Hill and Technology MARA
11
Pearson-Prentice Hall
 Overview of Quantitative Approaches

1. Naive approach
2. Moving averages
Time-Series
3. Weighted Moving Averages Models
4. Exponential smoothing
5. Trend projection
Associative
6. Linear regression Model

5/20/2019
Faculty of Mechanical Engineering,
NY- MEM 575: Courtesy of Mc University
Graw Hill and Technology MARA
12
Pearson-Prentice Hall
 Time Series Forecasting
 Set of evenly spaced numerical data
 Obtained by observing response variable at
regular time periods
 Forecast based only on past values, no other
variables important
 Assumes that factors influencing past and
present will continue influence in future

5/20/2019
Faculty of Mechanical Engineering,
NY- MEM 575: Courtesy of Mc University
Graw Hill and Technology MARA
13
Pearson-Prentice Hall
 Time Series Components

Trend Cyclical

Seasonal Random

5/20/2019
Faculty of Mechanical Engineering,
NY- MEM 575: Courtesy of Mc University
Graw Hill and Technology MARA
14
Pearson-Prentice Hall
 Components of Demand
Trend
component
Seasonal peaks
Demand for product or service

Actual
demand

Average demand
over four years
Random
variation
| | | |
1 2 3 4
Year Figure 4.1
5/20/2019
Faculty of Mechanical Engineering,
NY- MEM 575: Courtesy of Mc University
Graw Hill and Technology MARA
15
Pearson-Prentice Hall
 Trend Component
1. Persistent, overall upward or downward
pattern
2. Changes due to population, technology,
age, culture, etc.
3. Typically several years duration

5/20/2019
Faculty of Mechanical Engineering,
NY- MEM 575: Courtesy of Mc University
Graw Hill and Technology MARA
16
Pearson-Prentice Hall
 Seasonal Component
1. Regular pattern of up and down
fluctuations
2. Due to weather, customs, etc.
3. Occurs within a single year
Number of
Period Length Seasons
Week Day 7
Month Week 4-4.5
Month Day 28-31
Year Quarter 4
Year Month 12
Year Engineering,
Faculty of Mechanical
NY- MEM 575:
Week
Courtesy of Mc University
52
Graw Hill and Technology MARA
5/20/2019 17
Pearson-Prentice Hall
 Cyclical Component
1. Repeating up and down movements
2. Affected by business cycle, political, and
economic factors
3. Multiple years duration
4. Often causal or
associative
relationships
0 5 10 15 20
5/20/2019
Faculty of Mechanical Engineering,
NY- MEM 575: Courtesy of Mc University
Graw Hill and Technology MARA
18
Pearson-Prentice Hall
 Random Component
1. Erratic, unsystematic, ‘residual’ fluctuations
2. Due to random variation or unforeseen
events
3. Short duration and
non-repeating

M T W T F
5/20/2019
Faculty of Mechanical Engineering,
NY- MEM 575: Courtesy of Mc University
Graw Hill and Technology MARA
19
Pearson-Prentice Hall
 Naive Approach
 Assumes demand in next
period is the same as
demand in most recent period
 e.g., If January sales were 68, then February
sales will be 68
 Sometimes cost effective and efficient
 Can be good starting point

5/20/2019
Faculty of Mechanical Engineering,
NY- MEM 575: Courtesy of Mc University
Graw Hill and Technology MARA
20
Pearson-Prentice Hall
 Techniques for Averaging

1. Moving average
2. Weighted moving average
3. Exponential smoothing

5/20/2019
Faculty of Mechanical Engineering,
NY- MEM 575: Courtesy of Mc University
Graw Hill and Technology MARA
21
Pearson-Prentice Hall
 Moving Average Method
1. MA is a series of arithmetic means
2. Used if little or no trend
3. Used often for smoothing
 Provides overall impression of data over time

∑ demand in previous n periods

Moving average =
n

5/20/2019
Faculty of Mechanical Engineering,
NY- MEM 575: Courtesy of Mc University
Graw Hill and Technology MARA
22
Pearson-Prentice Hall
 Moving Average Example
Actual 3-Month
Month Sales Moving Average
January 10
February 12
March 13
April 16 (10 + 12 + 13)/3 = 11 2/3
May 19 (12 + 13 + 16)/3 = 13 2/3
June 23 (13 + 16 + 19)/3 = 16
July 26 (16 + 19 + 23)/3 = 19 1/3

5/20/2019
Faculty of Mechanical Engineering,
NY- MEM 575: Courtesy of Mc University
Graw Hill and Technology MARA
23
Pearson-Prentice Hall
 Graph of Moving Average

Moving
30 –
Average
28 –
Forecast
26 – Actual
24 – Sales
22 –
Sales

20 –
18 –
16 –
14 –
12 –
10 –
| | | | | | | | | | | |
J F M A M J J A S O N D

5/20/2019
Faculty of Mechanical Engineering,
NY- MEM 575: Courtesy of Mc University
Graw Hill and Technology MARA
24
Pearson-Prentice Hall
 Weighted Moving Average

1. Used when trend is present

 Older data usually less important
2. Weights based on experience and intuition

∑ (weight for period n)

Weighted x (demand in period n)
moving average =
∑ weights

5/20/2019
Faculty of Mechanical Engineering,
NY- MEM 575: Courtesy of Mc University
Graw Hill and Technology MARA
25
Pearson-Prentice Hall
 Weights Applied Period
Weighted Moving Average
3 Last month
2 Two months ago
1 Three months ago
6 Sum of weights

Actual 3-Month Weighted

Month Sales Moving Average
January 10
February 12
March 13
April 16 [(3 x 13) + (2 x 12) + (10)]/6 = 121/6
May 19 [(3 x 16) + (2 x 13) + (12)]/6 = 141/3
June 23 [(3 x 19) + (2 x 16) + (13)]/6 = 17
July 26 [(3 x 23) + (2 x 19) + (16)]/6 = 201/2

5/20/2019
Faculty of Mechanical Engineering,
NY- MEM 575: Courtesy of Mc University
Graw Hill and Technology MARA
26
Pearson-Prentice Hall
 Moving Average And
Weighted Moving Average
Weighted
30 – moving
average
25 –
Sales demand

20 – Actual
sales
15 –
Moving
10 – average

5 –
| | | | | | | | | | | |
J F M A M J J A S O N D
Figure 4.2
5/20/2019
Faculty of Mechanical Engineering,
NY- MEM 575: Courtesy of Mc University
Graw Hill and Technology MARA
27
Pearson-Prentice Hall
 Potential Problems With
Moving Average

1. Increasing n smoothens the forecast but makes

it less sensitive to changes
2. Do not forecast trends well
3. Require extensive historical data

5/20/2019
Faculty of Mechanical Engineering,
NY- MEM 575: Courtesy of Mc University
Graw Hill and Technology MARA
28
Pearson-Prentice Hall
 Exponential Smoothing

1. Form of weighted moving average

 Weights decline exponentially
 Most recent data weighted most
2. Requires smoothing constant ()
 Ranges from 0 to 1
 Subjectively chosen
3. Involves little record keeping of past data

5/20/2019
Faculty of Mechanical Engineering,
NY- MEM 575: Courtesy of Mc University
Graw Hill and Technology MARA
29
Pearson-Prentice Hall
 Exponential Smoothing
Remember This!!!!!!!!
New forecast = Last period’s forecast
+  (Last period’s actual demand
– Last period’s forecast)

Ft = Ft – 1 + (At – 1 - Ft – 1)

where Ft = new forecast

Ft – 1 = previous forecast
 = smoothing (or weighting)
constant (0 ≤  ≤ 1)
5/20/2019
Faculty of Mechanical Engineering,
NY- MEM 575: Courtesy of Mc University
Graw Hill and Technology MARA
30
Pearson-Prentice Hall
 Choosing 
The objective is to obtain the most accurate forecast no
matter the technique; lowest forecast error indicates
better accuracy.

Forecast error = Actual demand - Forecast value

= At - Ft

5/20/2019
Faculty of Mechanical Engineering,
NY- MEM 575: Courtesy of Mc University
Graw Hill and Technology MARA
31
Pearson-Prentice Hall
 Forecast Accuracy
(Common Measures of Error) – MAD #1
Error: difference between actual value and forecast value
1. Mean Absolute Deviation (MAD)
 Average absolute error
{this value is computed by taking the sum of the absolute
values of the individual forecast errors and dividing by the
number of periods of data (n)}

∑ |Actual - Forecast|
MAD =
n

5/20/2019
Faculty of Mechanical Engineering,
NY- MEM 575: Courtesy of Mc University
Graw Hill and Technology MARA 32
Pearson-Prentice Hall
 Forecast Accuracy
(Common Measures of Error)-MSE #2

2. Mean Squared Error (MSE)

 Average of squared error;
{ 2nd method of measuring overall forecast error; the average
of the squared differences between forecasted and observed
values}.

∑ (Actual - Forecast )2
MSE =
n

5/20/2019
Faculty of Mechanical Engineering,
NY- MEM 575: Courtesy of Mc University
Graw Hill and Technology MARA 33
Pearson-Prentice Hall
 Forecast Accuracy
(Common Measures of Error)-MAPE #3

3. Mean Absolute Percent Error (MAPE)

 Average absolute percent error
{ the average of the absolute value difference betrween the
forecasted and the actual values; expressed in %}

n
MAPE = ∑100|Actuali - Forecasti|/Actuali

i=1 n

5/20/2019
Faculty of Mechanical Engineering,
NY- MEM 575: Courtesy of Mc University
Graw Hill and Technology MARA 34
Pearson-Prentice Hall
 Common Measures of Error or Forecast
Accuracy
1) Mean Absolute Deviation (MAD)
∑ |Actual - Forecast|
MAD =
n
2) Mean Squared Error (MSE)
∑ (Actual - Forecast )2
MSE =
n
3) Mean Absolute Percent Error (MAPE)
n
MAPE = ∑100|Actuali - Forecasti|/Actuali

i=1 n
5/20/2019
Faculty of Mechanical Engineering,
NY- MEM 575: Courtesy of Mc University
Graw Hill and Technology MARA
35
Pearson-Prentice Hall
 Exponential Smoothing Example

Predicted demand = 142 Ford Mustangs

Actual demand = 153
Smoothing constant  = .20

5/20/2019
Faculty of Mechanical Engineering,
NY- MEM 575: Courtesy of Mc University
Graw Hill and Technology MARA
36
Pearson-Prentice Hall
 Exponential Smoothing Example

Predicted demand = 142 Ford Mustangs

Actual demand = 153
Smoothing constant  = .20

New forecast = 142 + .2(153 – 142)

5/20/2019
Faculty of Mechanical Engineering,
NY- MEM 575: Courtesy of Mc University
Graw Hill and Technology MARA
37
Pearson-Prentice Hall
 Exponential Smoothing Example

Predicted demand = 142 Ford Mustangs

Actual demand = 153
Smoothing constant  = .20

New forecast = 142 + .2(153 – 142)

= 142 + 2.2
= 144.2 ≈ 144 cars

5/20/2019
Faculty of Mechanical Engineering,
NY- MEM 575: Courtesy of Mc University
Graw Hill and Technology MARA
38
Pearson-Prentice Hall
 Exponential Smoothing Example 2
Demand for the last four months was:

Predict demand for July using each of these methods:

(A)
1) A 3-period moving average
2) exponential smoothing with alpha equal to .20 (use naïve to begin).
(B)
3) If the naive approach had been used to predict demand for April through June,
what would MAD have been for those months?

5/20/2019
Faculty of Mechanical Engineering,
NY- MEM 575: Courtesy of Mc University
Graw Hill and Technology MARA
39
Pearson-Prentice Hall
 Exponential Smoothing Example 2
A) 1.
2.
(8+10+8)/3 = 8.67 (July Forecast)
Use naïve to begin Ft = Ft – 1 + (At – 1 - Ft – 1)
Month Demand Forecast
March 6 -
April 8 6
May 10 6 + 0.2(8 – 6) = 6.4
June 8 6.4 + 0.2(10 – 6.4) = 7.12
7.12 + 0.2(8 – 7.12) = 7.296

Month March April May June

B)
Demand 6 8 10 8
Naïve - 6 8 10
Absolute Error - 2 2 2

MAD = (2+2+2) /3 = 2

5/20/2019
Faculty of Mechanical Engineering,
NY- MEM 575: Courtesy of Mc University
Graw Hill and Technology MARA
40
Pearson-Prentice Hall
 Other Examples
Moving Average

Weekly sales of ten-grain bread at the local organic food market are in the table
below. Based on this data, forecast week 9 using a five-week moving average.

Week 1 2 3 4 5 6 7 8

Sales 415 389 420 382 410 432 405 421

(382+410+432+405+421)/5 = 410.0

5/20/2019
Faculty of Mechanical Engineering,
NY- MEM 575: Courtesy of Mc University
Graw Hill and Technology MARA
41
Pearson-Prentice Hall
 Other Examples
Exponential Smoothing & MAD
Jim's department at a local department store has tracked the sales of a product over the last
ten weeks. Forecast demand using exponential smoothing with an alpha (α) of 0.4, and an
initial forecast of 28.0. Calculate MAD, MSE and MAPE.
Period Demand
1 24
2 23
3 26
4 36
5 26
6 30
7 32
8 26
9 25
10 28

5/20/2019
Faculty of Mechanical Engineering,
NY- MEM 575: Courtesy of Mc University
Graw Hill and Technology MARA
42
Pearson-Prentice Hall
 Other Examples –F = F t t–1 + (At – 1 - Ft – 1)
Exponential Smoothing
Demand
Forecast І At – FtІ ( At – Ft)2 100*І At – FtІ / At
Period (Actual) Error
Ft І errorІ (error) 2 100 (І error І/actual)
At
1 24 28.00 -4 4 16 16.6 %
2 23 26.40 -3.40 3.40 11.56 14.78 %
3 26 25.04 0.96 0.96 0.92 3.69 %
4 36 25.42 10.58 10.58 111.94 29.39 %
5 26 29.65 -3.65 3.65 13.32 14.04%
6 30 28.19 1.81 1.81 3.28 6.03%
7 32 28.92 3.08 3.08 9.49 9.63 %
8 26 30.15 -4.15 4.15 17.22 15.96 %
9 25 28.49 -3.49 3.49 12.18 13.96%
10 28 27.09 0.91 0.91 0.83 3.25%
Total -1.36 36.03 196.74 127.33 %
Average -0.14 3.6 19.6 12.73 %
Bias MAD MSE MAPE

5/20/2019
Faculty of Mechanical Engineering, University Technology MARA 43
 Let’s Recap
1. Discuss the overview of forecasting techniques
2. Compare and contrast qualitative and quantitative approaches to
forecasting
3. Apply the naive, moving averages, weighted moving averages and
exponential smoothing methods.
4. Compute and analyze three measures of forecast accuracy; MAD,
MSE and MAPE

5/20/2019
Faculty ofNY-
Mechanical Engineering,
MEM 575: Courtesy of Mc GrawUniversity Technology MARA
Hill and Pearson-Prentice
44
Hall
5/20/2019
Faculty of Mechanical Engineering,
NY- MEM 575: Courtesy of Mc University
Graw Hill and Technology MARA
45
Pearson-Prentice Hall
 Thank you
46
Faculty of Mechanical Engineering, University Technology MARA
December 24, 2013 Footer text here
 Other Examples –F = F t t–1 + (At – 1 - Ft – 1)
Exponential Smoothing
Demand
Forecast І At – FtІ ( At – Ft)2 100*І At – FtІ / At
Period (Actual) Error
Ft І errorІ (error) 2 100 (І error І/actual)
At
1 254 -
2 259 254 5
3 253 254+0.2(5)=255 -2
255+0.2(-2)=
4 268
254.2
5 264
6 265
7 257

Average -0.14 3.6 19.6 12.73 %

Bias MAD MSE MAPE

5/20/2019
Faculty of Mechanical Engineering, University Technology MARA 47