Operations

Managemen Forecasting
t Lecture 2
 Learning Objectives
Chapter 4

• Understand the three time

horizons and which models
apply for each.
• Explain when to use each of
the four qualitative models.
• Apply the naive, moving-
average, exponential
smoothing, and trend methods.
Add a footer 2
 Quantitative methods of
OM Forecasting
 FR
Time-Series Forecasting - Naïve Forecast

Naïve forecast
 Uses a single previous value of a time series as the basis for a forecast
The forecast for a time period is equal to the previous time period’s value
 Can be used with
A stable time series
Seasonal variations
Trend

Add a footer 4
 FR
Time-Series Forecasting - Naïve Forecast
Naïve method: =, where

t=current period

 Advantages

 Simple to use, virtually no cost

 Easily understandable

Disadvantage: Relies entirely on one past period, highly influenced by randomness of that
period

Add a footer 5
 FR
Time-series Forecasting–Averaging Methods

These techniques work best when a series tends to vary about an average

 Averaging techniques smooth variations in the data

 They exhibit less variability than the actual data

Techniques used:

 Moving average

 Weighted moving average

 Exponential smoothing

Add a footer 6
 FR
Moving Average
• Technique that averages a number of the most recent actual values in
generating a forecast
n

A t i
At  n  ...  At  2  At 1
Ft  MA n  i 1

n n
where
Ft  Forecast for time period t
MA n  n period moving average
At i  Actual value in period t  i
n  Number of periods in the moving average
3-7
 FR
Simple Moving Average

S

Solution
 FR
Simple Moving Average

S
Moving Average-Example FR

Period Demand
3 period MA 6 period MA
1 10
2 20
3 5
4 15 11.67
5 17 13.33
6 23 12.33
7 18 18.33 15.00
8 30 19.33 16.33
9 40 23.67 18.00
10 50 29.33 23.83
11 55 40.00 29.67
12 70 48.33 36.00

2-21
 FR
Moving Average-Example
80
60
DEMAND Actual Demand
40 3 PMA
20 6 PMA

0
1 3 5 7 9 11 PERIOD
Questions:
Why is 3-P MA longer than 6-P MA
Which curve fluctuate the most?
Which curve is the smoothest?
2-22
 FR
Moving Average (cont.)
• As new data become available, the forecast is updated by adding the
newest value and dropping the oldest and then re-computing the
average
• The number of data points included in the average determines the
model’s sensitivity
• Fewer data points used—more responsive
• More data points used—less responsive

• A possible disadvantage is that all values are weighted equally

3-12
 FR
Weighted Moving Average
• The most recent values in a time series are given more weight in computing a
forecast
• The choice of weights, w, is somewhat arbitrary and involves some trial and error

Ft  wt ( At )  wt 1 ( At 1 )  ...  wt  n ( At  n )
where
wt  weight for period t , wt 1  weight for period t  1, etc.
At  the actual value for period t , At 1  the actual value for period t  1, etc.

3-13
Weighted Moving Average FR
Example
 FR
Exponential Smoothing
• A weighted averaging method that is based on the previous forecast
plus a percentage of the forecast error

Ft  Ft 1   ( At 1  Ft 1 )
where
Ft  Forecast for period t
Ft 1  Forecast for the previous period
 = Smoothing constant
At 1  Actual demand or sales from the previous period

3-15
Forecast Accuracy and Control FR

Allowances should be made for forecast errors

 It is important to provide an indication of the extent to which the
forecast might deviate from the value of the variable that actually occurs
Forecast errors should be monitored
 Error = Actual – Forecast
 If errors fall beyond acceptable bounds, corrective action may be
necessary
 FR
Forecast Accuracy Metrics

MAD 
 Actual t  Forecast t MAD weights all errors evenly

 Actual t  Forecast t 
2
MSE weights errors according to their
MSE  squared values
n 1

Actualt  Forecast t
 Actualt
 100 MAPE weights errors according to
MAPE  relative error
n

3-17
LO 3.5
Forecast Error Calculation FR
Actua Forecas
Perio l t (A-F)
d Error | [|Error|/
(A) (F) Error| Error 2
Actual]x100
1 107 110 -3 3 9 2.80%
2 125 121 4 4 16 3.20%
3 115 112 3 3 9 2.61%
4 118 120 -2 2 4 1.69%
5 108 109 1 1 1 0.93%
Sum 13 39 11.23%
n=5 n-1 = 4 n=5
MAD MSE MAPE
= 2.6 = 9.75 = 2.25%
3-18
 FR
Monitoring the Forecast
 Tracking forecast errors and analyzing them can provide useful insight into whether
forecasts are performing satisfactorily
 Sources of forecast errors:
 The model may be inadequate due to
a. omission of an important variable
b. a change or shift in the variable the model cannot handle
c. the appearance of a new variable
 Irregular variations may have occurred
 Random variation
 Control charts are useful for identifying the presence of non-random error in forecasts
 Tracking signals can be used to detect forecast bias

3-19
 FR
Exercise 1

Add a footer 20
 FR
Exercise 2

Add a footer 21
 Thank You.
OM
Operations Management
Disraeli Asante-Darko, PhD
+233 0248 00 33 41
[email protected]