RMIT Classification: Trusted
Operations Management
Week 2
Forecasting
The best way to predict the future is to create it.
Abraham Lincoln
RMIT Classification: Trusted
You should be able to:
1. Compare and contrast qualitative and
quantitative approaches to forecasting
2. Describe time series and associative models
3. Explain three measures of forecast accuracy
4. Explain about Tracking Signal
3
RMIT Classification: Trusted
Forecast – a statement about the future value of a
variable of interest
We make forecasts about such things as weather,
demand, and resource availability
Forecasts are an important element in making informed
decisions
4
RMIT Classification: Trusted
Qualitative Forecasting
Qualitative techniques permit the inclusion of soft information such as:
Human factors
Personal opinions
Hunches
These factors are difficult, or impossible, to quantify
Quantitative Forecasting
Quantitative techniques involve :
1. Time series: the projection of historical data
2. Associative model: attempts to use causal variables to make a forecast
These techniques rely on hard data
5
RMIT Classification: Trusted
Forecasts that project patterns identified in
recent time-series observations
Time-series - a time-ordered sequence of
observations taken at regular time intervals
Assume that future values of the time-series can
be estimated from past values of the time-series
6
RMIT Classification: Trusted
Trend
Seasonality
Cycles
Irregular variations
Random variation
7
RMIT Classification: Trusted
8
RMIT Classification: Trusted
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
9
RMIT Classification: Trusted
These Techniques work best when a series tends to
vary about an average
Averaging techniques smooth variations in the data
They can handle step changes or gradual changes in the
level of a series
Techniques
1. Moving average
2. Weighted moving average
3. Exponential smoothing
10
RMIT Classification: Trusted
Technique that averages a number of the most recent
actual values in generating a forecast
n
A t i
Ft MA n i 1
n
actual demand period 1 actual demand period 2 ... actual demand period n
n
where
Ft Forecast for time period t
MA n n period moving average
At 1 Actual value in period t 1
n Number of periods in the moving average
11
RMIT Classification: Trusted
Demand for product A is given in the following table. Forecast using
moving average with n=3 for Period 5.
Period 1 2 3 4 5 6 7 8
Actual demand 10 12 11 13 14 12 13 12
compare
Answer:
F5 = (12+11+13)/3 = 12.03
Note: You can use Data Analysis package in Excel to forecast using Moving
Average method. Please see the Data Analysis [Link] on Canvas
12
RMIT Classification: Trusted
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 )
( weight period 1* actual demand period 1 weight period 2 * actual demand period 2
... weight period n * actual demand period n) /( sum of weights )
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.
in above formula 0 w 1,
w t
1
13
RMIT Classification: Trusted
Demand for product A is given in the following table. Forecast
using weighted moving average with n=2 for period 6.
Weight for latest period =0.7
Weight for old period = 0.3
Period 1 2 3 4 5 6 7 8
Answer:
Actual demand 10 12 11 13 14 12 13 12
F6 = 14(0.7)+13(0.3)= 13.7
compare
14
RMIT Classification: Trusted
Smoothing
constant
0≤ α≤1
Forecast of
period t Actual
Forecast of
previous demand of
period previous
period
15
RMIT Classification: Trusted
Demand for product A is given in the following table. Forecast using
exponential smoothing for period 3 using alpha=0.2.
Period 1 2 3 4 5 6 7 8
Answer:Actual demand 10 12 11 13 14 12 13 12
F2= F1+0.2(A1-F1) F1 is unknown
Assumption: A1=F1
F2 = 10 + 0.2 (10-10) =10
F3 = 10 + 0.2 (12-10) =10.4
16
RMIT Classification: Trusted
• A simple data plot can reveal the existence and nature of a
trend
• Linear trend equation
b= Slope of
the line
t= Time period
17
RMIT Classification: Trusted
Method 1: Use Line Chart in Excel
Method 2: TREND formula
Method 3: Data Analysis package
Method 4: Manual method
n ty t y
b
n t 2
t
2
a
y b t
or y bt
n
where
n Number of periods
y Value of the time series
18
RMIT Classification: Trusted
Associative techniques are based on the
development of an equation that summarizes
the effects of predictor variables
Predictor variables - variables that can be used to
predict values of the variable of interest
Home values may be related to such factors as home and
property size, location, number of bedrooms, and number
of bathrooms
19
RMIT Classification: Trusted
1. Variations around the line are random
2. Deviations around the average value (the line)
should be normally distributed
3. Predictions are made only within the range of
observed values
20
RMIT Classification: Trusted
3-21
a = Value of Y b= Slope of
when x = 0 the line
Y =Dependent
x=Independent
variable
variable
21
RMIT Classification: Trusted
Method 1: Slope and intercept using the following formula:
Finding values of a and b for Regression using:
a. Graph
b. Excel formula
c. Data Analysis package
d. Manual method
22
RMIT Classification: Trusted
Forecasters want to minimize forecast errors
It is nearly impossible to correctly forecast real-world
variable values on a regular basis
So, 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 accuracy should be an important forecasting
technique selection criterion
Error = Actual – Forecast
If errors fall beyond acceptable bounds, corrective action
may be necessary
23
RMIT Classification: Trusted
MAD
Actual t Forecast t MAD weights all errors
n evenly
Actual t Forecast t
2
MSE weights errors according
MSE to their squared values
n 1
Actualt Forecast t
Actualt
100
MAPE weights errors
MAPE
n according to relative error
24
RMIT Classification: Trusted
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
Tracking signals can be used to detect forecast bias
25
RMIT Classification: Trusted
26
RMIT Classification: Trusted
The manager of a travel agency has been using a seasonally
adjusted forecast to predict demand for packaged tours.
The actual and predicted values are as follows:
Period Demand Predicted
1 129 124
2 194 200
3 156 150 Compute a tracking signal for
4 91 94 periods 5 through 14 using the
5 85 80
6 132 140 initial and updated MADs with
7 126 128 alpha = 0.3.
8 126 124
9 95 100 If limits of 4 are used, what can
10 149 150 you conclude?
11 98 94
12 85 80
13 137 140
Excel solution is available on Canvas
14 134 128
27
RMIT Classification: Trusted
Step 1
Step 2
Cum. Tracking
Predicte |e| MADt
Period Demand Error Error Signal
d
1 129 124 5 5 5
2 194 200 –6 6 –1
3 156 150 6 6 5
4 91 94 –3 3 2
5 85 80 5 5 7 5.00 1.40
Step 4
6 132 140 –8 8 –1 5.90 –0.17
7 126 128 –2 2 –3 4.73 –0.63
8 126 124 2 2 –1 3.91 –0.26
9 95 100 –5 5 –6 4.24 –1.42
10 149 150 –1 1 –7 3.27 –2.14
11 98 94 4 4 –3 3.49 –0.86
12 85 80 5 5 2 3.94 0.51
13 137 140 –3 3 –1 3.66 –0.27
14 134 128 6 6 5 4.36 1.15
Step 3
Conclusion: As all tracking signals are within the limits of 4 28
then we can conclude the no issue regarding the error was found.
RMIT Classification: Trusted
Questions
29
