Failure Prevention and

Recovery
(Forecasting)

1
Failure Prevention (forecasting)
• Demand Management

• Qualitative Forecasting Methods

• Simple & Weighted Moving Average Forecasts

• Exponential Smoothing

• Simple Linear Regression

2
Demand Management

Independent Demand

A Dependent Demand

B(4) C(2)

D(2) E(1) D(3) F(2)

3
Independent Demand
• Take an active role to influence demand

• Take a passive role and simply respond to demand

4
Types of Forecasts
• Qualitative (Judgmental)

• Quantitative
• Time Series Analysis
• Causal Relationships
• Simulation

5
 Components of Demand

What’s going on here?

x
x x
x x
x x
x x
x x x
Sales

xx x x
x xx x x
x
x
x x x x x x
x x x x x x
x x x
x xxxxx
x
x x

1 2 3 4
Year 6
A Trend is Worth Noting
• Start by identifying the trend

• What is the trend in the sales of personal computers?

• Are there any seasonal effects, cyclical factors or other

predicted events that might affect the sales of personal
computers?

7
Qualitative Methods
• Grass Roots

• Market Research

• Panel Consensus

8
Qualitative Methods
• Executive Judgment

• Historical Analogy

• Delphi Method

9
 Delphi Method

l. Choose the experts to participate. There should be a

variety of knowledgeable people in different areas.

2. Through a questionnaire (or E-mail), obtain forecasts

(and any premises or qualifications for the forecasts)
from all participants.

3. Summarize the results and redistribute them to the

participants along with appropriate new questions .

10
Delphi Method
4. Summarize again, refining forecasts and conditions,
and again develop new questions.

5. Repeat Step 4 if necessary. Distribute the final

results to all participants.

11
 Judgmental Forecasting Applications
Small and Large Firms

Low High
Sales Sales
Technique < $100M > $500M
Manager’s opinion 40.7% 39.6%
Jury of executive opinion 40.7% 41.6%
Sales force composite 29.6% 35.4%
Number of Firms 27 48

Source: Nada Sanders and Karl Mandrodt (1994) “Practitioners Continue to Rely on Judgmental Forecasting
Methods Instead of Quantitative Methods,” Interfaces, vol. 24, no. 2, pp. 92-100.

12
 Quantitative Forecasting Applications
Small and Large Firms
Low High
Sales Sales
Technique < $100M > $500M
Moving average 29.6% 29.2%
Straight line projection 14.8% 14.6%
Naive 18.5% 14.6%
Exponential smoothing 14.8% 20.8%
Regression 22.2% 27.1%
Simulation 3.7% 10.4%
Classical decomposition 3.7% 8.3%
Box-Jenkins 3.7% 6.3%
Number of Firms 27 48
Source: Nada Sanders and Karl Mandrodt (1994) “Practitioners Continue to Rely on Judgmental Forecasting
Methods Instead of Quantitative Methods,” Interfaces, vol. 24, no. 2, pp. 92-100.

13
Time Series Analysis
Pick a model based on:

1. Time horizon to forecast

2. Data availability
3. Accuracy required
4. Size of forecasting budget
5. Availability of qualified personnel

14
Simple Moving Average
• Let’s develop 3-week and 6-week moving average
forecasts for demand.
Week Demand
• Assume you only have 3 weeks and 6 weeks of actual
1 650
demand
2 data
678 for the respective forecasts
3 720
4 785
5 859
At-1 + At-2 + At-3 +...+At-n
6 920 Ft =
7 850 n
8 758
9 892
10 920
11 789
12 844
15
Week Demand 3-Week 6-Week
1 650
2 678
3 720
4 785 682.67
5 859 727.67
6 920 788.00
7 850 854.67 768.67
8 758 876.33 802.00
9 892 842.67 815.33
10 920 833.33 844.00
11 789 856.67 866.50
12 844 867.00 854.83
16
 950
900
850
800 Demand
Demand

750
3-Week
700
650 6-Week
600
550
500
1 2 3 4 5 6 7 8 9 10 11 12
Week

Last Update:October 16, 2022

17
In-Class Exercise
• Develop 3-week and 5-week moving average forecasts
for demand.
• Assume you only have 3 weeks and 5 weeks of actual
demand data for the respective forecasts
Week Demand
1 820
2 775
3 680
4 655
5 620
6 600
7 575

18
In-Class Exercise (Solution)

Week Demand 3-Week 5-Week

1 820
2 775
3 680
4 655 758.33
5 620 703.33
6 600 651.67 710.00
7 575 625.00 666.00

19
Weighted Moving Average

Ft = w 1A t-1 + w 2 A t-2 + w 3 A t-3 +...+w n A t-n

n

w
i=1
i =1

Determine the 3-period

Week Demand
1 650
weighted moving average
2 678 forecast for period 4.
3 720
Weights:
4
t-1 .5
t-2 .3
t-3 .2

20
Solution

Week Demand Forecast

1 650
2 678
3 720
4 693.4

F=
4 .5(720)+.3(678)+.2(650)
21
In-Class Exercise

Determine the 3-period

weighted moving average
Week Demand
forecast for period 5.
1 820
2 775 Weights:
3 680 t-1 .7
4 655 t-2 .2
t-3 .1

22
Solution

Week Demand Forecast

1 820
2 775
3 680
4 655
5 672

23
Exponential Smoothing
• 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

Ft = Ft-1 + (At-1 - Ft-1)

24
Exponential Smoothing Example
• Determine exponential smoothing forecasts for periods
2-10 using =.10 and =.60. Week Demand
1 820
2 775
• Let F1=D1 3 680
4 655
5 750
6 802
7 798
8 689
9 775
10
25
Week Demand 0.1 0.6
1 820 820.00 820.00
2 775 820.00 820.00
3 680 815.50 820.00
4 655 801.95 817.30
5 750 787.26 808.09
6 802 783.53 795.59
7 798 785.38 788.35
8 689 786.64 786.57
9 775 776.88 786.61
10 776.69 780.77

26
 Effect of  on Forecast

850
800
750 Demand
Demand

700 0.1
650
600 0.6
550
500
1 2 3 4 5 6 7 8 9 10
Week

27
In-Class Exercise

Week Demand
Determine exponential
1 820 smoothing forecasts for
2 775 periods 2-5 using =.50
3 680
4 655
5 Let F1=D1

28
In-Class Exercise (Solution)

Week Demand 0.5

1 820 820.00
2 775 820.00
3 680 797.50
4 655 738.75
5 696.88

29
Forecast Errors
• Study the formula for a moment

• Now, what does MAD tell you?

n

A
t=1
t - Ft
MAD = 1 MAD  0.8 standard deviation
n
1 standard deviation  1.25 MAD

30
Example--MAD
Determine the MAD for the four forecast periods
Month Sales Forecast
1 220 n/a
2 250 255
3 210 205
4 300 320
5 325 315

31
Solution

Month Sales Forecast Abs Error

1 220 n/a
2 250 255 5
3 210 205 5
4 300 320 20
5 325 315 10

40
n

A
t=1
t - Ft
40
MAD = = = 10
n 4

32
Tracking Signal
• Is the forecast average keeping pace with any genuine
upward or downward changes?

RSFE Running sum of forecast errors

TS = =
MAD Mean absolute deviation

33
What do you notice?

40
35
Sales

30
25
20
0 1 2 3 4 5 6 7 8 9 10 11
Period

34
Simple Linear Regression Model
• b is similar to the slope. However, since it is calculated
with the variability of the data
Y in mind, its formulation is
not as straight-forward as our usual notion of slope

Yt = a + bx 0 1 2 3 4 5 x (weeks)

35
Calculating a and b

a = y - bx

 xy - n(y)(x)
b= 2 2
 x - n(x )

36
Regression Equation Example

Week Sales
1 150
2 157
3 162
4 166
5 177
Develop a regression equation to predict sales
based on these five points.

37
 Week Week*Week Sales Week*Sales
1 1 150 150
2 4 157 314
3 9 162 486
4 16 166 664
5 25 177 885
3 55 162.4 2499
Average Sum Average Sum

b=
 xy - n(y)(x) 2499 - 5(162.4)(3) 63
=  = 6.3
 x - n(x )
2 2
55  5(9 ) 10

a = y - bx = 162.4 - (6.3)(3) = 143.5

38
 y = 143.5 + 6.3t
180
175
170
165
160 Sales
Sales

155 Forecast
150
145
140
135
1 2 3 4 5

Period
39
Learning Curves
• Underlying Principles of Learning Curves

• Plotting Learning Curves

• Learning

• From Learning Curves to Performance Improvement

 Underlying Principles of Learning Curves
1. Each time you perform a task it takes less time than the
last time you performed the same task

2. The extent of task time decrease decreases over time

3. The reduction in time will follow a predictable pattern

Last Update:October 16, 2022

Plotting Learning Curves

Initial Manufacturing Cost: $100/unit

$100
90% Learning Curve: $90
$81
$73
$66
$59
$53
$48
$43
Plotting Learning Curves

90 % Learning Curve

120
Production Cost($)

100
80
60
40
20
0
0 1000 2000 3000 4000 5000
Unit
Learning
• Individual Learning

• Organizational Learning
From Learning Curves to Performance
Improvement
• Proper selection of workers.
• Proper training.
• Motivation.
• Work specialization.
• Do one or very few jobs at a time.
• Provide quick and easy access for help.
• Allow workers to help redesign their tasks.