Chapter two

Forecasting

By Belachew M. 1
 Outline
Introduction
Importance of Forecasting
Components of Demand
Types of Forecasting Methods
Selection of Forecasting Models

By Belachew M. 2
 Introduction
 Forecasting is a tool used for predicating future demand based on past demand
information to reduce uncertainty.
 Forecasts are concerned with determining what the future will look like while planning
is concerned with what it should look like.
 Forecasts affect decisions and activities throughout an organization.
 Accounting, finance
 Human resources, Marketing and Operations
 Product / service design
Why forecasting is important?
 Demand for products and services is usually uncertain. So analyzing the previous and
the present data it can be estimate the futures activities, forms the basis of planning.
 Forecasting can be used for…
 Strategic planning (long range planning)
 Finance and accounting (budgets and cost controls)
 Marketing (future sales, new products)
 Production and operations
By Belachew M. 3
 Importance of Forecasting
 Marketing managers:
 Use sales forecasts to determine optimal sales force allocations.
 Set sales goals.
 Plan promotions and advertising.
 Planning for capital investments:
 Predictions about future economic activity.
 Estimating cash inflows accruing from the investment.
 The personnel department:
 Planning for human resources.

4
 Importance of Forecasting Cont.…
 Managers of nonprofit institutions:
 Forecasts for budgeting purposes.
 Universities:
 Forecast student enrollments.
 Cost of operations.
 Funds to be provided by tuition and by government appropriations.
 The bank has to forecast:
 Demands of various loans and deposits
 Money and credit conditions so that it can determine the cost of money it
lends.

5
 Importance of Forecasting Cont.…
 Manufacturers:
 Worker absenteeism
 Machine availability
 Material costs
 Transportation and production lead times, etc.
 Service providers:
 Forecasts of population
 Demographic variables
 Weather, etc.

6
 Types of Forecasts
1. Economic forecasts- Predict a variety of economic
indicators, like money supply, inflation rates, interest
rates, etc.
2. Technological forecasts- Predict rates of technological
progress and innovation.
3. Demand forecasts- Predict the future demand for a
company’s products or services.

By Belachew M. 7
 Components of Demand

Six components of demand:

i. Average demand
ii. Trend: occurs when demand is increasing or
decreasing over time as a result of some factor such as
word of mouth, advertising, or changes in the
population.
iii. Seasonal component: occurs with products and
services that relate to certain months or time periods of
the year.

By Belachew M. 8
 Components of demand…..

iv. Cyclical components: similar to seasonal factors but have a

much longer time period and are often harder to identify.

Cyclical factors include politics, economic conditions, war, and

sociocultural influences.

v. Autocorrelation: occurs when the value of one data point is

highly correlated with past values.

vi. Random variation: caused by chance events after all the

other five components have been accounted for.

By Belachew M. 9
 Components of Demand
 Trend
 Seasonal element
 Cyclical elements
 Random variation

By Belachew M. 10
Steps in the forecasting process

By Belachew M. 11
 Types of forecasts by time horizon
 Short-range Forecast
Quantitative methods

 Usually < 3 months

• Job scheduling, worker assignments
 Medium-range forecast Detailed use of system

– 3 months to 2 years
– Sales/production planning
 Long-range forecast
– > 2 years
– New product planning Design of system
Qualitative methods

By Belachew M. 12
Types of Forecasting Methods
A. Qualitative or judgmental methods

By Belachew M. 13
 Qualitative Methods….
 Executive Judgment: Opinion of a group of high level experts or
managers is pooled.
 Market Research/Survey: Petitions input from customers pertaining to
their future purchasing plans. It involves the use of questionnaires,
consumer panels and tests of new products and services.
 Delphi Method: It is forecasting techniques applied to subjective nature
demand values. It is useful when there is no historical data from which to
develop statistical models and when managers inside the firm have no
experience. As a forecasting tool, it is useful for technological
forecasting, that is, for assessing changes in technology and their impact
on an organization. Often the goal is to predict when a certain event will
occur.

By Belachew M. 14
 Type Characteristics Strengths Weaknesses
Executive A group of managers Good for strategic or One person's opinion
opinion meet & come up with new-product can dominate the
a forecast forecasting forecast

Market Uses surveys & Good determinant of It can be difficult to

research interviews to identify customer preferences develop a good
customer preferences questionnaire

Delphi Seeks to develop a Excellent for Time consuming to

method consensus among a forecasting long-term develop
group of experts product demand,
technological
changes, and
By Belachew M. 15
Quantitative Forecasting Methods

By Belachew M. 16
 Con…
i. Time-series Methods: Quantitative methods will be adopted when
sufficient quantitative information available and when little or no
qualitative information available.
 Time series forecasting models try to predict the future based on past data.

By Belachew M. 17
 Quantitative Forecasting Methods……
1. Naïve approach:
 Assumes demand in next period is the same as demand in most recent
period
 Next period forecast = Last Period’s actual ----- Ft 1  At
 Simple to use
 Sometimes cost effective and efficient
 Quick and easy to prepare
 Data analysis is nonexistent
 Easily understandable
 Cannot provide high accuracy
e.g. If the sales forecast for the month June were 48, then July sales
will be 48.
By Belachew M. 18
 Con…
2. Moving Average
i. Simple moving average
 Uses average demand for a fixed sequence of periods.
 Stable demand with no pronounced behavioral patterns.
 Assumes an average is a good estimator of future behavior
– Used if little or no trend
– Used for smoothing
 A smaller N makes the forecast more responsive.
 A larger N makes the forecast more stable.

By Belachew M. 19
 Quantitative Forecasting Methods……
a simple moving average: A technique that averages a number
of recent actual values, updated as new values become
available.
 In the simple moving average models the forecast value is
given by;

t is the current period.

Ft+1 is the forecast for next period
n is the forecasting horizon (how far
back we look),
A is the actual sales figure from each
period.
By Belachew M. 20
 Quantitative Forecasting Methods……
Example1: apply a 3-month moving average
forecast for the following orders.
Months Demand(y) Forecast
January 120
February 90
March 100
April 75
May 110
June 50
July 75
August 130
September 110
October 90
November ?
By Belachew M. 21
 Quantitative Forecasting Methods……
Example1: apply a 3-month moving average forecast for the
following orders.

Months Demand(y) Forecast

January 120 -
February 90 - What if the forecasting
March 100 - period is 5 months
April 75 103.33 moving average?
May 110 88.33
June 50 95
July 75 78.33
August 130 78.33
What you observed?
September 110 85
October 90 105
November ? 110
By Belachew M. 22
 Quantitative forecasting methods……
Smoothing effect

In general
 5 month average smooth's
data more;
 3 month average more
responsive.

By Belachew M. 23
 Quantitative Forecasting Methods……
ii. Weighted Moving Average: it is similar to a moving average, except that it
assigns more weight to the most recent values in a time series.
 Gives more emphasis to recent data
 Weights decrease for older data
 The sum of all weights equals 1.

where;
Wt=Weight for the period t, At = Actual value in period t,
Wn= weight for the period t-n+1, and
At-n+1= Actual value in period t-n+1,

By Belachew M. 24
 Quantitative Forecasting Methods……

Example2: Forecast for month 5?

Month 1 Month 2 Month3 Month 4 Month 5

100 90 105 95 ?

 Take 40 percent of the actual sales for the most recent month,
30 percent of two months ago, 20 percent of three months ago,
and 10 percent of four months ago.

By Belachew M. 25
 Quantitative Forecasting Methods……

 The forecast for month 5 would be :

F5 = 0.40(95) +0.30(105)+ 0.20(90)+ 0.10(100)

= 38 +31.5+ 18+10

= 97.5

By Belachew M. 26
 Con…
3. Exponential smoothing method: In this method, weights are assigned in
exponential order. The weights decrease exponentially from most recent demand
data to older demand data.

By Belachew M. 27
 Quantitative Forecasting Methods……

NB: if we are not given the forecast value for the first period assume
forecasted value is equals to the actual value.

Example3: for the following demand data calculate the forecasted

demand, for the month of June at α=0.1
Forecaste
Months Demand(y) d
What is the forecast at
January 1325 1370 α=0.8 and compare the
February 1353 result!

March 1305
April 1275
May 1210
June ?
By Belachew M. 28
 Quantitative Forecasting Methods……

NB: if we are not given the forecast value for the first period assume
forecasted value is equals to the actual value.

Example3: for the following demand data calculate the forecasted

demand, for the month of June at α=0.1
Forecaste
Months Demand(y) d
What is the forecast at
January 1325 1370 α=0.8 and compare the
February 1353 1365.5 result!
March 1305 1364.25
April 1275 1358.33
May 1210 1350
June ? 1336
By Belachew M. 29
Quantitative Forecasting Methods……
Impact of The Value of α

By Belachew M. 30
 Quantitative Forecasting Methods……

Choosing appropriate Value of ᾳ

 If real demand is stable: small ᾳ

 If real demand is rapidly increasing or decreasing large ᾳ

to try to keep up with the change.

By Belachew M. 31
 Con…
ii. Regression/Causal analysis method
 In this method, past demand data is used to establish a functional relationship
between two variables. One variable is known or assumed to be known; and used to
forecast the value of other unknown variable (i.e. demand).
 In the discussion of regression analysis, we showed how one or more independent
variables could be used to predict the value of a single dependent variable. If we can
identify a good set of related independent, or predictor, variables we may be able to
develop an estimated regression equation for predicting or forecasting the time series.
 The value of Correlation Coefficient (r) is such that -1 < r < +1. The + and – signs are
used for positive linear correlations and negative linear correlations, respectively.
 Positive correlation: If x and y have a strong positive linear correlation, r is close to +1.
An r value of exactly +1 indicates a perfect positive fit. Positive values indicate a
relationship between x and y variables such that as values for x increases, values for y
also increase.
 Negative correlation: If x and y have a strong negative linear correlation, r is close to -1.
An r value of exactly -1 indicates a perfect negative fit. Negative values indicate a
relationship between x and y such that as values for x increase, values for y decrease.
 No correlation: If there is no linear correlation or a weak linear correlation, r is Close
to 0. A value near zero means that there is a random, nonlinear relationship between
the two variables
By Belachew M. 32
 Causal Models
 Often, leading indicators can help to predict changes in
future demand.
 Causal models establish a cause-and-effect relationship
between independent and dependent variables.
 A common tool of causal modeling is linear regression:
 Additional related variables may require multiple
regression modeling.

Y  a  bX
 Y- Dependent Variable
 X- Independent Variable
By Belachew M. 33
 Linear Regression

 Identify dependent (Y) and

independent (X) variables
 Solve for the slope of the
b
 XY  X  Y  line:
 X 2  X  X 
b
 XY  n XY

 X  nX
2 2

 Solve for the y intercept:

a  Y  bX
 Develop your equation for
the trend line:
 Y=a + bX

By Belachew M. 34
 Linear Regression- Example
 TOSHIBA has been tracking the relationship between sales
and advertising dollars. Use linear regression to find out
what sales might be if the company invested $53 in
advertising next year using the following previous data.

b
 XY  n XY
Sales $ Adv.$ XY X^2 Y^2
 X  nX
2 2
(Y) (X)
1 130 32 4160 2304 16,900
28202  447.25147.25
b  1.15
9253  447.25
2 151 52 7852 2704 22,801 2

a  Y  b X  147.25  1.1547.25
3 150 50 7500 2500 22,500
4 158 55 8690 3025 24964
a  92.9
5 153.85 53
Y  a  bX  92.9  1.15X
Tot 589 189 28202 9253 87165
Y  92.9  1.1553  153.85
Avg 147.25 47.25

By Belachew M. 35
 Correlation Coefficient
 Correlation coefficient (r) measures the direction and
strength of the linear relationship between two variables.
The closer the r value is to 1.0 the better the regression
line fits the data points.
n XY    X  Y 
r
 
n  X   X  * n  Y  Y  
2 2
2 2

428,202  189589
r  .982
4(9253)- (189) * 487,165  589
2 2

r 2  .982  .964
2

 Coefficient of determination (r2) measures the amount of

variation in the dependent variable about its mean that is
explained by the regression line. Values of (r2) close to 1.0
are desirable.
3
 Measures of Forecast Error
 Mean Absolute Deviation (MAD)
 Measures the total error in a forecast without regard to sign
 Cumulative Forecast Error (CFE)
 Also called running sum of forecast error (RSFE)
 Measures any bias in the forecast
 Mean Square Error (MSE)
 Penalizes larger errors

n

 t t 
n


2
A t - Ft A - F
t =1 t =1
MAD = MSE =
n n
n

CFE   actual  forecast RSFE  (At  Ft )

i 1
 Ideal values = 0 (i.e., no forecasting error) 37
 Measuring Accuracy: Tracking signal

 The tracking signal is a measure of how often our

estimations have been above or below the actual value. It
is used to decide when to re-evaluate using a model.

n RSFE
RSFE  (At  Ft ) TS 
i1
MAD

 Positive tracking signal: most of the time actual values

are above our forecasted values
 Negative tracking signal: most of the time actual values
are below our forecasted values
Usually 3 ≤ TS ≥ 8, out of this range investigate!
By Belachew M. 38
 Selecting the Right Forecasting Model
 Selecting the right forecasting methods depends on:

1. The amount & type of available data

 Some methods require more data than others

2. Degree of accuracy required

 Increasing accuracy means more data

3. Length of forecast horizon

 Forecast accuracy decreases as time horizon
increases(Different models for 3 month vs. 10) years

4. Presence of data patterns

By Belachew M. 39
 Application of Forecasting

 Forecasts are vital to every business organization and for

every significant management decision.
 Sales Forecasting : Any company in selling goods needs
to forecast the demand for those goods.
 Forecasting Economic Trends : forecasting economic
trends on a regional, national, or even international level.
 Forecasting Staffing Needs:
 Forecasting in education environment :
 Ministry of Petroleum :
 Department of Technology:
By Belachew M. 40
By Belachew M. 41