FORECASTING

Forecasting
Planning is an integral part of a
manager’s job. If uncertainties
cloud the planning horizon,
managers will find it difficult to
plan effectively.
 Forecasting
• Forecasts help managers by reducing
some of the uncertainty, thereby
enabling them to develop more
meaningful plans.

• A forecast is a statement about the

future.
• There are two uses for forecasts.

• One is to help managers plan the

system, and the other is to help
them plan the use of the system
 Features Common to all Forecasts
1. Forecasting techniques generally
assume that the same underlying
causal system that existed in the past
will continue to exist in the future.
2. Forecast are rarely perfect; actual
results usually differ from predicted
values.

3. Forecasts for groups of items tend

.to be more accurate than forecasts for
individual item
4.Forecast accuracy decreases as the
time period covered by the forecasts –
the time horizon – increases.

Generally speaking, short range forecasts

must contend with fewer uncertainties than
longer range forecasts.
Approaches to Forecasting
A. Forecast based on judgment and opinion
– Rely on analysis of subjective inputs obtained
from various sources:
• Executive opinions
• Sales force composite
• Consumer surveys
• Outside opinion
• Opinions of managers and staff
Approaches to Forecasting
B. Forecast based on time series data

Time series - a time ordered sequence of

observations taken at regular intervals over
time.
• The behavior can be described as
follows:
–Trend
–Seasonality
–Cycles
–Irregular variations
–Random variations
Techniques for Averaging
1. Naïve Forecasts

• A naive forecasts for any period

equals the previous period’s actual
value.

• For example, if demand last week was

50 units, the naïve forecasts for the
upcoming week is 50 units.
 Techniques for Averaging
2. Moving Averages

Techniques that averages a number of

recent actual values, updated as new
values become available.
where:
i = “age “ of the data (i=1,2,3….)
n = number of periods in the moving average

MAn = Ai = actual value with age i

n MA = forecast
Example:
Compute a three-period moving average forecast given
demand for shopping carts for the last five periods.
PERIOD AGE DEMAND
1 5 42
2 4 40
3 3 43
4 2 40
5 1 41

MA3 = 43 + 40 + 41 / 3 = 41.33

If actual demand in period 6 turns out to be 39,

the moving average forecast for period 7 would be:
MA3 = 40+41+39 / 3 = 40
Example 2.
Given the following demand data:
a. Compute a weighted average forecast using a weight of 0.40 for
the most recent period, 0.30 fo the next most recent, 0.20 for the
next and 0.10 for the next.
b. If the actual demand for period 6 is 39, forecast demand for
period 7 using the same weights as in part a. Period Demand
1 42
2 40
3 43
4 40
Solution: 5 41

a. Forecast = 0.40(41 )+ 0.30(40) + 0.20(43)+0.10(40) =

b. Forecast = 0.40(39 )+ 0.30(41 ) + 0.20(40)+0.10(43) =
Exponential Smoothing
Exponential smoothing – weighted averaging
method based on previous forecast plus a
percentage of the forecast error.

Next forecast = previous forecast + ᾳ(actual –previous

forecast)
The closer its value is to zero, the slower the
forecast will be to adjust to forecast errors
(i.e. the greater the smoothing).

Conversely, the closer the value of ᾳ is to

1.00, the less the smoothing.

Commonly used values of ᾳ range from 0.05

to 0.50
A number of different approaches can be used
to obtain a starting forecast:

such as the average of the first several periods;

a subjective estimate;

or the fist actual value as the forecast for period

2.

For simplicity, the naïve approach I used in

the example
Example

Use exponential smoothing to develop a series

of forecasts for the following data, and compute
the error for each period.

a. Use a smoothing constant of 0.10

b. use a smoothing constant of 0.40

Example:
Period (t) Actual demand
1 42

2 40

3 43

4 40

5 41

6 39

7 46

8 44

9 45

10 38

11 40

12
Solution:
Ft = 42 + 0.10(40-42) = 41.8

Then, if the actual demand turns out to be

43, the next forecast would be:

Ft = 41.8 + 0.10(43 – 41.8) = 41.92

Period (t) Actual Demand ᾳ = 0.10 ᾳ = 0.40

Forecast Error Forecast Error

1 42 - - - -

2 40 42 -2 42 -2

3 43 41.8 1.2 41.2 1.8

4 40 41.92 -1.92 41.92 -1.92

5 41

6 39

7 46

8 44

9 45

10 38

11 40

12
Technique for Trend
Linear Trend Equation
The trend component of a time
series reflects the effects of any long
term factors on the series. The trend
component may be linear or it may
not.
Linear Trend Equation

Yt = a + bt
t = specified number of time periods
from t= 0
yt = forecast for period t
a = value of yt at t = 0
b = slope of the line
Value of ∑t and ∑t2
n ∑t ∑t2
1 1 1
2 3 5
3 6 14
4 10 30
5 15 55
6 21 91
7 28 140
8 36 204
9 45 285
10 55 385
11 66 506
12 78 650
13 91 819
14 105 1015
15 120 1240
16 136 1496
17 153 1785
18 171 2109
19 190 2470
20 210 2870
b = n∑ty - ∑t∑y / n∑t 2 - (∑t)2

a = ∑y - b∑t / n
where:
n = number of periods
Y = value of the time series
Sample Problem Week Unit sales

1 700
Calculator sales for a 2 724
California based firm over
3 720
the last 10 weeks are shown
4 728
in the following table. Plot
5 740
the data, and visually check
to see if a linear trend would 6 742

be appropriate. Then 7 758

determine the equation of 8 750

the trend line, and predict 9 770

sales for weeks 11 and 12. 10 775

Solution
Week (t) Unit sales (y) ty

1 700 700

2 724 1448

3 720 2160 b=
4 728 2912

5 740 3700
a=
6 742 4452 Y11 =
7 758 5306

8 750 6000
Y12 =
9 770 6930

10 775 7750

7407 41,358
Associative Forecasting techniques
Simple linear regression

Associative techniques rely on identification

of related variables that can be used to predict
values of the variable interest.

The essence of associative techniques is the

development of an equation that summarizes the
effects of predictor variables. The primary method
of analysis is known as regression
 The simplest and most widely used form
of regression involves a linear relationship
between two variables.

The object in linear regression is to obtain

an equation of a straight line. This least squares
line has the equation:
Y = predicted (dependent) variable
X = predictor (independent) variable
b = slope of the line

Y = a + bx a = value of y when x = 0
(the height of the line at the y
intercept)
b = n(∑xy) – (∑x) (∑y) / n(∑X2) - (∑x)2

a = ∑y – b∑x / n

Where:

n = number of paired observations

Example
Healthy hamburgers has a chain of
12 stores in USA. sales figures and
profits for the stores are given in the
following table. Obtain a regression
line for the data, and predict profit for
a store assuming sales of 10 million
dollars.
 Profits (y) in million
Sales (x) in million dollars Sales (x) Profits
dollars in million (y) in
dollars million XY X2 Y2
$7 $0.15 dollars

2 0.10
$7 $0.15

6 0.13 2 0.10

4 0.15 6 0.13 b=
14 0.25 4 0.15

15 0.27 14 0.25 a=
15 0.27
16 0.24
16 0.24
Yc =
12 0.20
12 0.20
14 0.27
14 0.27
20 0.44
20 0.44

15 0.34
15 0.34

7 0.17 7 0.17
Correlation
Measures the strength and direction of relationship
between two variables.

Correlation can range from -1.00 to +1.00.

A correlation of +1.00 indicates that changes in one

variable are always matched by changes in the other.

A correlation of -1.00 indicates that increases in one

variable are matched by decreases in the other.

A correlation close to zero indicates little linear

relationship between two variables.
 2 2 2 2
r = n(∑xy) - (∑x) (∑y) / √n(∑x )- (∑x) . √n(∑y ) - (∑y)
Sample problem:
Sales of 19-inch color television sets
and three-month lagged
unemployment are shown in the
following table. Determine if
unemployment levels can be used to
predict demand for 19-inch color TVs
and, if so, derived a predictive
equation.
Period 1 2 3 4 5 6 7 8 9 10 11

Units sold
20 41 17 35 25 31 38 50 15 19 14
Unemployment %
7.2 4.0 7.3 5.5 6.8 6.0 5.4 3.6 8.4 7.0 9.0

x y xy X2 Y2
r = ________________
7.2 20
Compute the regression
line

b = _______________

a = _______________

y = a + bx
END