9/15/2023 Abiot Tsegaye(BA, MBA, PhD) 1

What is forecasting?
 Forecasting is about predicting the future as accurately
as possible, given all the information available
including historical data and knowledge of any future
events that might impact the forecasts.
 A forecast is an estimate of uncertain future events
(literally, to "cast forward" by extrapolating from past
and current data).
 It is a basic input in the decision processes of
management because it provides information on
future events.

9/15/2023 Abiot Tsegaye(BA, MBA, PhD) 2

Why is forecasting?
 Even though forecast is almost always in error, it is better to
have the limited information provided by a forecast than to
make decisions in total ignorance about the future.
 Forecasts are the basis for budgeting, planning capacity,
sales, production and inventory, personnel, purchasing,
and more.
 Forecasts play an important role in the planning process
because they enable managers to anticipate the future so
they can plan accordingly.
 Forecasts affect decisions and activities throughout an
organization, in accounting, finance, human resources,
marketing, and management information systems (MIS),
as well as in operations and other parts of an organization.

9/15/2023 Abiot Tsegaye(BA, MBA, PhD) 3

Principles and features of Forecasting
 The forecast should be timely. Usually, a certain
amount of time is needed to respond to the
information contained in a forecast.
 The forecast should be close to accurate, and the
degree of accuracy should be stated.
 The forecast should be reliable and valid.
 The forecast should be expressed in meaningful units.
Financial planners need to know how many dollars
will be needed, production planners need to know
how many units will be needed, and … so on.
9/15/2023 Abiot Tsegaye(BA, MBA, PhD) 4
Cont…
 The forecast should be in writing. Although this will
not guarantee that all concerned are using the same
information, a written forecast will permit an objective
basis for evaluating the forecast once actual results are
in.
 The forecasting technique should be simple to
understand and use. Users often lack confidence in
forecasts based on sophisticated techniques.
 The forecast should be cost-effective: The benefits
should outweigh the costs.

9/15/2023 Abiot Tsegaye(BA, MBA, PhD) 5

Steps in the Forecasting Process
 Determine the purpose of the forecast.
 Properly answer questions such as what needs to be
forecasted, the reason, level of detail, units of analysis & time
horizon required
 Obtain, clean, and analyze appropriate data.
 Obtaining the data can involve significant effort. Once
obtained, the data may need to be “cleaned” to get rid of
outliers and obviously incorrect data before analysis.
 Select a forecasting technique.
 Make the forecast.
 Monitor the forecast.
 A forecast has to be monitored to determine whether it is
performing in a satisfactory manner.

9/15/2023 Abiot Tsegaye(BA, MBA, PhD) 6

 Types of Forecasting Methods
 Forecasting methods are classified into two groups:

9/15/2023 Abiot Tsegaye(BA, MBA, PhD) 7

 Qualitative Methods
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
9/15/2023 Abiot Tsegaye(BA, MBA, PhD) 8
 Quantitative Methods
 Time Series Models:
 Assumes information needed to generate a forecast is
contained in a time series of data
 Assumes the future will follow same patterns as the past
 Causal Models or Associative Models
 Explores cause-and-effect relationships
 Uses leading indicators to predict the future

9/15/2023 Abiot Tsegaye(BA, MBA, PhD) 9

 Time Series Models
 Forecaster looks for data patterns as
 Data = historic pattern + random variation

 Historic pattern to be forecasted:

 Level (long-term average) – data fluctuates around a constant
mean
 Trend – data exhibits an increasing or decreasing pattern
 Seasonality – any pattern that regularly repeats itself and is of a
constant length
 Cycle – patterns created by economic fluctuations

 Random Variation cannot be predicted

9/15/2023 Abiot Tsegaye(BA, MBA, PhD) 10

 Time Series Patterns

9/15/2023 Abiot Tsegaye(BA, MBA, PhD) 11

 Time Series Methods
 Naive: Ft 1  At
 The forecast is equal to the actual value observed
during the last period – good for level patterns
 Simple Mean: Ft 1   A t / n

 The average of all available data - good for level

patterns
 Moving Average: F   A / n t 1 t

 The average value over a set time period

(e.g.: the last four weeks)
 Each new forecast drops the oldest data point &
adds a new observation
 More responsive to a trend but still lags behind
actual data

9/15/2023 Abiot Tsegaye(BA, MBA, PhD) 12

 Time Series Methods con’t
 Weighted Moving Average: Ft 1   C t A t

 All weights must add to 100% or 1.00

e.g. Ct .5, Ct-1 .3, Ct-2 .2 (weights add to 1.0)

 Allows emphasizing one period over others; above

indicates more weight on recent data (Ct=.5)

 Differs from the simple moving average that weighs all

periods equally - more responsive to trends

9/15/2023 Abiot Tsegaye(BA, MBA, PhD) 13

 Time Series Methods con’t
 Exponential Smoothing: Ft 1  αA t  1  α Ft
Most frequently used time series method because of
ease of use and minimal amount of data needed
 Need just three pieces of data to start:
 Last period’s forecast (Ft)
 Last periods actual value (At)
 Select value of smoothing coefficient, ,between 0 and 1.0
 If no last period forecast is available, average the last
few periods or use naive method
 Higher values (e.g. .7 or .8) may place too much
weight on last period’s random variation

9/15/2023 Abiot Tsegaye(BA, MBA, PhD) 14

 Time Series forecasting example
 Determine forecast for periods
Period Actual
7&8
 2-period moving average 1 300
 4-period moving average 2 315
 2-period weighted moving average 3 290
with t-1 weighted 0.6 and t-2
4 345
weighted 0.4
5 320
 Exponential smoothing with
alpha=0.2 and the period 6 6 360
forecast being 375 7 375
8

9/15/2023 Abiot Tsegaye(BA, MBA, PhD) 15

 Time Series Problem Solution
Period Actual 2-Period 4-Period 2-Per.Wgted. Expon. Smooth.
1 300
2 315
3 290
4 345
5 320
6 360
7 375 340.0 328.8 344.0 372.0
8 367.5 350.0 369.0 372.6

9/15/2023 Abiot Tsegaye(BA, MBA, PhD) 16

 Linear Trend Line
A time series technique that computes a forecast with trend
by drawing a straight line through a set of data using this
formula:
Y = a + bx where
Y = forecast for period X
X = the number of time periods from X = 0
A = value of y at X = 0 (Y intercept)
B = slope of the line

9/15/2023 Abiot Tsegaye(BA, MBA, PhD) 17

 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

9/15/2023 Abiot Tsegaye(BA, MBA, PhD) 18

 Linear Regression
 Identify dependent (y) and
independent (x) variables
 Solve for the slope of the line

b
 XY  X  Y   XY  n X Y
 X 2  X  X  b 
 X  nX
2 2

 Solve for the y intercept

a  Y  bX
Develop your equation for the
trend line

Y=a + bX

9/15/2023 Abiot Tsegaye(BA, MBA, PhD) 19

Linear Regression Problem: A maker of golf shirts has been tracking the relationship
between sales and advertising dollars. Use linear regression to find out what sales might
be if the company invested $53,000 in advertising next year.
Sales $ Adv.$ XY X^2 Y^2 b   XY  n XY
(Y) (X)
 X  nX2 2

1 130 32 4160 2304 16,900

2 151 52 7852 2704 22,801
3 150 50 7500 2500 22,500 28202  447.25147.25
b  1.15
9253  447.25 
2

4 158 55 8690 3025 24964 a  Y  b X  147.25  1.1547.25 

a  92.9
5 153.85 53 Y  a  bX  92.9  1.15X
Y  92.9  1.1553  153.85
Tot 589 189 28202 9253 87165
Avg 147.25 47.25

9/15/2023 Abiot Tsegaye(BA, MBA, PhD) 20

 Correlation Coefficient
How Good is the Fit?
 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 (r 2) 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.

9/15/2023 Abiot Tsegaye(BA, MBA, PhD) 21

 Multiple Regression
 An extension of linear regression but:
 Multiple regression develops a relationship between a
dependent variable and multiple independent variables.
The general formula is:

9/15/2023 Abiot Tsegaye(BA, MBA, PhD) 22

 Measuring Forecast Error
 Forecasts are never perfect
 Need to know how much we should rely
on our chosen forecasting method
 Measuring forecast error:

E t  A t  Ft
 Note that over-forecasts = negative errors
and under-forecasts = positive errors

9/15/2023 Abiot Tsegaye(BA, MBA, PhD) 23

 Measuring Forecasting Accuracy

 Mean Absolute Deviation (MAD) MAD   actual  forecast

 measures the total error in a forecast n
without regard to sign
 Cumulative Forecast Error (CFE) CFE 
 Measures any bias in the forecast
 actual  forecast
 actual - forecast 2

 Mean Square Error (MSE) MSE 

 Penalizes larger errors
n

9/15/2023 Abiot Tsegaye(BA, MBA, PhD) 24

Selecting the Right Forecasting Model
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
 Different models for 3 month vs. 10 years
4. Presence of data patterns
 Lagging will occur when a forecasting model
meant for a level pattern is applied with a trend

9/15/2023 Abiot Tsegaye(BA, MBA, PhD) 25

 Forecasting Software
 Spreadsheets
 Microsoft Excel, Quattro Pro, Lotus 1-2-3
 Limited statistical analysis of forecast data
 Statistical packages
 SPSS, SAS, NCSS, Minitab
 Forecasting plus statistical and graphics
 Specialty forecasting packages
 Forecast Master, Forecast Pro, Autobox, SCA

9/15/2023 Abiot Tsegaye(BA, MBA, PhD) 26

 Guidelines for Selecting Software
 Does the package have the features you want?
 What platform is the package available for?
 How easy is the package to learn and use?
 Is it possible to implement new methods?
 Do you require interactive or repetitive
forecasting?
 Do you have any large data sets?
 Is there local support and training available?
 Does the package give the right answers?

9/15/2023 Abiot Tsegaye(BA, MBA, PhD) 27

 REFERENCES
 Chase, R.B., Jacobs, F.R. and Aquilano, N.J. (2006) Operations
Management for Competitive Advantage with Global Cases. McGraw-
Hill/Irwin, Boston.
 Gaither & Frazier, Operations Management, Cengage, New Delhi
 Panner Selvem, Production and Operation Management, Prentice Hall of
India.
 Chunnawals, Production & 9*/89Operation Management Himalaya,
Mumbai
 Kanishka Bedi, Production & Operation Management, University Press.
 Upendra Kachru: Operation Management, Excel Publications.
 Adam, E.E& Ebert; R.J. Production and Operation Management, 6th Ed.,
Prentice Hall
 Chary , S.N.Production and Operation Management, New Delhi, Tata
McGraw Hill

9/15/2023 Abiot Tsegaye(BA, MBA, PhD) 28