© Dr. Muhammad Wasif
Operations &
Production Management
(OPM)
Dr. Muhammad Wasif
Visiting Faculty, IBA.
6 – Forecasting
Resource Person : Dr. Muhammad Wasif Operations & Production Management www 2
www
1
Topic 6 Forecasting
© Dr. Muhammad Wasif
Section 6.1
Introduction to Forecasting
Resource Person : Dr. Muhammad Wasif Operations & Production Management www 3
Forecasting
Process of estimating a future event
Underlying basis of all business
decisions
Production
Inventory
Personnel
Facilities
Resource Person : Dr. Muhammad Wasif Operations & Production Management www 4
www
2
Topic 6 Forecasting
© Dr. Muhammad Wasif
Applications of Forecasting
Accounting Cost/profit estimates
Resource Person : Dr. Muhammad Wasif Operations & Production Management www 5
Medium-range forecast
Short-range
3 months to 3 years forecasting
Sales and production planning, budgeting
3+ years
New product planning, facility location, research and
development
Resource Person : Dr. Muhammad Wasif Operations & Production Management www 6
www
3
Topic 6 Forecasting
© Dr. Muhammad Wasif
Types of Forecasts
Economic forecasts
Address business cycle – inflation rate, money
supply, housing starts, etc.
Technological forecasts
Predict rate of technological progress
Impacts development of new products
Demand forecasts
Predict sales of existing products and services
Resource Person : Dr. Muhammad Wasif Operations & Production Management www 7
Resource Person : Dr. Muhammad Wasif Operations & Production Management www 8
www
4
Topic 6 Forecasting
© Dr. Muhammad Wasif
Timely
Seldom Perfect
Reliable
Based on Assumptions
Reality
Accurate
Ideal
Written
Accuracy decreases as time
horizon increases
Easy to use
Resource Person : Dr. Muhammad Wasif Operations & Production Management www 9
Approaches to Forecast
Qualitative Methods
Used when situation is vague and little data exist; for example New
products, New technology
Quantitative Methods
Used when situation is ‘stable’ and historical data exist; for example Existing
products, Current technology
www
5
Topic 6 Forecasting
© Dr. Muhammad Wasif
2. Delphi Method
Resource Person : Dr. Muhammad Wasif Operations & Production Management www 11
www
6
Topic 6 Forecasting
© Dr. Muhammad Wasif
What consumers say, and what they actually do are often different
Resource Person : Dr. Muhammad Wasif Operations & Production Management www 13
1. Naive approach
2. Moving averages
time-series
models
3. Exponential smoothing
4. Trend projection
associative
5. Linear regression model
Resource Person : Dr. Muhammad Wasif Operations & Production Management www 14
www
7
Topic 6 Forecasting
© Dr. Muhammad Wasif
Section 6.2
Resource Person : Dr. Muhammad Wasif Operations & Production Management www 15
Resource Person : Dr. Muhammad Wasif Operations & Production Management www 16
www
8
Topic 6 Forecasting
© Dr. Muhammad Wasif
Seasonal Component
Number of
Regular pattern of up and down fluctuations Period Length Seasons
Week Day 7
Month Week 4-4.5
Due to weather, customs, etc. Month Day 28-31
Year Quarter 4
Year Month 12
Occurs within a single year Year Week 52
Resource Person : Dr. Muhammad Wasif Operations & Production Management www 17
Random Component
Erratic, unsystematic, ‘residual’ fluctuations
Resource Person : Dr. Muhammad Wasif Operations & Production Management www 18
www
9
Topic 6 Forecasting
© Dr. Muhammad Wasif
1- Naive Approach
Assumes demand in next
period is the same as demand in most recent period
Resource Person : Dr. Muhammad Wasif Operations & Production Management www 19
Resource Person : Dr. Muhammad Wasif Operations & Production Management www 20
www
10
Topic 6 Forecasting
© Dr. Muhammad Wasif
Actual 3-Month
Month Shed 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
Resource Person : Dr. Muhammad Wasif Operations & Production Management www 21
Resource Person : Dr. Muhammad Wasif Operations & Production Management www 22
www
11
Topic 6 Forecasting
© Dr. Muhammad Wasif
Resource Person : Dr. Muhammad Wasif Operations & Production Management www 24
www
12
Topic 6 Forecasting
© Dr. Muhammad Wasif
3 - Exponential Smoothing
Form of weighted moving average
Ranges from 0 to 1
Subjectively chosen
Resource Person : Dr. Muhammad Wasif Operations & Production Management www 25
3 - Exponential Smoothing
Predicted demand = 142 Ford Mustangs
Resource Person : Dr. Muhammad Wasif Operations & Production Management www 26
www
13
Topic 6 Forecasting
© Dr. Muhammad Wasif
Weight Assigned to
Most 2nd Most 3rd Most 4th Most 5th Most
Recent Recent Recent Recent Recent
Smoothing Period Period Period Period Period
Constant () (1 - ) (1 - ) 2 (1 - ) 3 (1 - )4
Resource Person : Dr. Muhammad Wasif Operations & Production Management www 27
Actual = .5
200 – demand
Demand
175 –
= .1
150 – | | | | | | | | |
1 2 3 4 5 6 7 8 9
Quarter
Resource Person : Dr. Muhammad Wasif Operations & Production Management www 28
www
14
Topic 6 Forecasting
© Dr. Muhammad Wasif
Choosing
The objective is to obtain the most accurate forecast no
matter the technique
= A t - Ft
Resource Person : Dr. Muhammad Wasif Operations & Production Management www 29
Resource Person : Dr. Muhammad Wasif Operations & Production Management www 30
www
15
Topic 6 Forecasting
© Dr. Muhammad Wasif
n
∑100|Actuali - Forecasti|/Actuali
MAPE = i=1
n
Resource Person : Dr. Muhammad Wasif Operations & Production Management www 31
Resource Person : Dr. Muhammad Wasif Operations & Production Management www 32
www
16
Topic 6 Forecasting
© Dr. Muhammad Wasif
∑ |deviations|
Rounded Absolute Rounded Absolute
MAD = Actual
Tonnage
Forecast
with
Deviation
for
Forecast
with
Deviation
for
n
Quarter Unloaded = .10 = .10 = .50 = .50
For1 = .10180 175 5.00 175 5.00
2 168 175.5 7.50 177.50 9.50
3
=159
82.45/8174.75
= 10.3115.75 172.75 13.75
For45 = .50175
190
173.18
173.36
1.82
16.64
165.88
170.44
9.12
19.56
6 =205
98.62/8175.02
= 12.3329.98 180.22 24.78
7 180 178.02 1.98 192.61 12.61
8 182 178.22 3.78 186.30 4.30
82.45 98.62
Resource Person : Dr. Muhammad Wasif Operations & Production Management www 33
errors)2Absolute
∑ (forecastRounded Rounded Absolute
MSE = Actual Forecast Deviation Forecast Deviation
Tonnage n with for with for
Quarter Unloaded = .10 = .10 = .50 = .50
For1 = .10180 175 5.00 175 5.00
2 168 175.5 7.50 177.50 9.50
3
= 1,526.54/8
159
= 190.82
174.75 15.75 172.75 13.75
For45 = .50175
190
173.18
173.36
1.82
16.64
165.88
170.44
9.12
19.56
6 = 1,561.91/8
205 = 195.24
175.02 29.98 180.22 24.78
7 180 178.02 1.98 192.61 12.61
8 182 178.22 3.78 186.30 4.30
82.45 98.62
Resource Person : Dr. Muhammad Wasif Operations & Production Management www 34
www
17
Topic 6 Forecasting
© Dr. Muhammad Wasif
Resource Person : Dr. Muhammad Wasif Operations & Production Management www 35
Resource Person : Dr. Muhammad Wasif Operations & Production Management www 36
www
18
Topic 6 Forecasting
© Dr. Muhammad Wasif
Resource Person : Dr. Muhammad Wasif Operations & Production Management www 37
Ft = (At - 1) + (1 - )(Ft - 1 + Tt - 1)
Tt = (Ft - Ft - 1) + (1 - )Tt - 1
Step 1: Compute Ft
Step 2: Compute Tt
Step 3: Calculate the forecast FITt = Ft + Tt
Resource Person : Dr. Muhammad Wasif Operations & Production Management www 38
www
19
Topic 6 Forecasting
© Dr. Muhammad Wasif
Resource Person : Dr. Muhammad Wasif Operations & Production Management www 39
Resource Person : Dr. Muhammad Wasif Operations & Production Management www 40
www
20
Topic 6 Forecasting
© Dr. Muhammad Wasif
Resource Person : Dr. Muhammad Wasif Operations & Production Management www 41
Resource Person : Dr. Muhammad Wasif Operations & Production Management www 42
www
21
Topic 6 Forecasting
© Dr. Muhammad Wasif
Resource Person : Dr. Muhammad Wasif Operations & Production Management www 43
25 –
20 –
15 –
0 – | | | | | | | | |
1 2 3 4 5 6 7 8 9
Time (month)
Resource Person : Dr. Muhammad Wasif Operations & Production Management www 44
www
22
Topic 6 Forecasting
© Dr. Muhammad Wasif
4 - Trend Projections
Fitting a trend line to historical data points to project
into the medium to long-range
Deviation5 Deviation6
Deviation3
Deviation4
Deviation1
(error) Deviation2
Trend line, y^ = a + bx
Time period
Resource Person : Dr. Muhammad Wasif Operations & Production Management www 46
www
23
Topic 6 Forecasting
© Dr. Muhammad Wasif
y^ = a + bx
xy - nxy
b=
x2 - nx2
a = y - bx
Resource Person : Dr. Muhammad Wasif Operations & Production Management www 47
www
24
Topic 6 Forecasting
© Dr. Muhammad Wasif
160 –
Trend line,
150 – y^ = 56.70 + 10.54x
140 –
Power demand
130 –
120 –
110 –
100 –
90 –
80 –
70 –
60 –
50 –
| | | | | | | | |
2003 2004 2005 2006 2007 2008 2009 2010 2011
Year
Resource Person : Dr. Muhammad Wasif Operations & Production Management www 50
www
25
Topic 6 Forecasting
© Dr. Muhammad Wasif
Resource Person : Dr. Muhammad Wasif Operations & Production Management www 51
Resource Person : Dr. Muhammad Wasif Operations & Production Management www 52
www
26
Topic 6 Forecasting
© Dr. Muhammad Wasif
Resource Person : Dr. Muhammad Wasif Operations & Production Management www 53
Resource Person : Dr. Muhammad Wasif Operations & Production Management www 54
www
27
Topic 6 Forecasting
© Dr. Muhammad Wasif
Resource Person : Dr. Muhammad Wasif Operations & Production Management www 55
Resource Person : Dr. Muhammad Wasif Operations & Production Management www 56
www
28
Topic 6 Forecasting
© Dr. Muhammad Wasif
2018 Forecast
140 – San Diego Hospital 2017 Demand
130 – 2016 Demand
2015 Demand
120 –
Demand
110 –
100 –
90 –
80 –
70 –
| | | | | | | | | | | |
J F M A M J J A S O N D
Time
Resource Person : Dr. Muhammad Wasif Operations & Production Management www 57
Section 6.3
Associative Forecasting
Resource Person : Dr. Muhammad Wasif Operations & Production Management www 58
www
29
Topic 6 Forecasting
© Dr. Muhammad Wasif
Associative Forecasting
Forecasting an outcome based on predictor variables
using the least squares technique
𝑦 a b·x
where 𝑦 computed value of the variable to be predicted
(dependent variable)
a = y-axis intercept
b = slope of the regression line
x = the independent variable though to predict the value of
the dependent variable
Resource Person : Dr. Muhammad Wasif Operations & Production Management www 59
2.0 –
1.0 –
| | | | | | |
0 1 2 3 4 5 6 7
Area payroll
Resource Person : Dr. Muhammad Wasif Operations & Production Management www 60
www
30
Topic 6 Forecasting
© Dr. Muhammad Wasif
Sales, y Payroll, x x2 xy
2.0 1 1 2.0
3.0 3 9 9.0
2.5 4 16 10.0
2.0 2 4 4.0
2.0 1 1 2.0
3.5 7 49 24.5
∑y = 15.0 ∑x = 18 ∑x2 = 80 ∑xy = 51.5
Resource Person : Dr. Muhammad Wasif Operations & Production Management www 61
| | | | | | |
0 1 2 3 4 5 6 7
Area payroll
Resource Person : Dr. Muhammad Wasif Operations & Production Management www 62
www
31
Topic 6 Forecasting
© Dr. Muhammad Wasif
Resource Person : Dr. Muhammad Wasif Operations & Production Management www 63
Tracking RSFE
signal =
MAD
∑(Actual demand in
period i -
Forecast demand
Tracking in period i)
signal =
∑|Actual - Forecast|/n)
Resource Person : Dr. Muhammad Wasif Operations & Production Management www 64
www
32
Topic 6 Forecasting
© Dr. Muhammad Wasif
Tracking Signal
0 MADs Acceptable
range
–
Lower control limit
Time
Resource Person : Dr. Muhammad Wasif Operations & Production Management www 65
Resource Person : Dr. Muhammad Wasif Operations & Production Management www 66
www
33
Topic 6 Forecasting
© Dr. Muhammad Wasif
Cumulative
Tracking Absolute Absolute
Actual Forecast
Signal Forecast Forecast
Qtr Demand Demand Error RSFE Error Error MAD
(RSFE/MAD)
1 90 =100
-10/10 -1 -10 -10 10 10 10.0
2 95 =100
-15/7.5 -2 -5 -15 5 15 7.5
0/10 = 0
3 115 100 +15 0 15 30 10.0
-10/10 = -1
4 100 110
+5/11 = +0.5 -10 -10 10 40 10.0
5 125 =110
+35/14.2 +2.5 +15 +5 15 55 11.0
6 140 110 +30 +35 30 85 14.2
Resource Person : Dr. Muhammad Wasif Operations & Production Management www 67
Section 6.4
Miscellaneous Forecasting
Resource Person : Dr. Muhammad Wasif Operations & Production Management www 68
www
34
Topic 6 Forecasting
© Dr. Muhammad Wasif
Adaptive Forecasting
Resource Person : Dr. Muhammad Wasif Operations & Production Management www 69
Focus Forecasting
Developed at American Hardware Supply, focus forecasting is
based on two principles:
1. Sophisticated forecasting models are not always better than
simple ones
2. There is no single technique that should be used for all
products or services
This approach uses historical data to test multiple
forecasting models for individual items
The forecasting model with the lowest error is then used to
forecast the next demand
Resource Person : Dr. Muhammad Wasif Operations & Production Management www 70
www
35
Topic 6 Forecasting
© Dr. Muhammad Wasif
References
Operations Management, 10th Ed., by J. Heizer &
B. Render
Operations Management, William J. Stevenson.
Operations Management, 7th Ed., N. Slack, A.B.
Jones, R. Johnston.
Cases in Operations Management, S. Chambers, C.
Harland, A. Harison, N. Slack.
Resource Person : Dr. Muhammad Wasif Operations & Production Management www 71
www
36