Chapter 3: Forecasting

I see that you will

get an A from this Course
.
Chapter Outline
 What is forecasting?
 Types of forecasts
 Time-Series forecasting
 Naïve
 Moving Average
 Exponential Smoothing
 Regression
 Good forecasts
Forecasting Introduction
 An essential aspect of managing any organization
is planning for the future.
 Organizations employ forecasting techniques to
determine future inventory, costs, capacities, and
interest rate changes.
 forecasting is A statement about the future value
of a variable of interest such as demand and a
tool used for predicting future value (demand)
based on past information.
 What is Forecasting?

 Process of predicting a future event underlying

basis of all business decisions:
 Production
 Inventory
 Personnel
 Facilities
There are two basic approaches to forecasting:
-Qualitative
-Quantitative
 Why do we need to forecast?
 Throughout the day we forecast very different
things such as weather, traffic, stock market, state
of our company from different perspectives.

 Virtually every business attempt is based on

forecasting.
Not all of them are derived from sophisticated
methods.
 However, “Best" educated guesses about future
are more valuable for purpose of Planning than no
forecasts and hence no planning.
 Importance of Forecasting
 Departments throughout the organization depend on
forecasts to formulate and execute their plans.
 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.
 to anticipate hiring or firing needs.
 Importance of Forecasting
 Managers of nonprofit institutions:
 Forecasts for budgeting purposes.
 Universities:
 Forecast student enrollments.
 Cost of operations.
 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.
 Principles of Forecasting

 There are many types of forecasting models. They differ in their degree
of complexity, the amount of data they use, and the way they generate
the forecast: However, some features are common to all forecasting
models. They include the following

 Forecasts rarely perfect because of randomness.

 Forecasts more accurate for groups vs. individuals.

 Forecast accuracy decreases as time horizon increases.

What types of forecasting?
 Economic forecasts
 Address business cycle – inflation rate, money supply,
housing starts, etc.
 Technological forecasts
 Predict rate of technological progress
 Impacts development of new products
 Demand forecasts
 Predict sales of existing product
Types of Forecasts by Time Horizon
Quantitativ
 Short-range forecast e
methods
 Usually < 3 months
 Job scheduling, worker assignments
Detailed
 Medium-range forecast use of
system
 3 months to 2 years
 Sales/production planning

 Long-range forecast
 > 2 years
Design
 New product planning
of system
Qualitative
Methods
 Steps of Forecasting

1. Decide what needs to be forecasted.

• Level of detail, units of analysis & time horizon required.

2. Evaluate and analyze appropriate data.

• Identify needed data & whether it’s available.

3. Select and test the forecasting model.

• Cost, ease of use & accuracy.

4. Generate the forecast.

5. Monitor forecast accuracy over time.

11
 Forecasting Techniques
Qualitative Methods
Used when situation is vague and little data exist.
 New products
 New technology
 Innovative products
Involves intuition, experience.
 Forecasts generated subjectively by the forecaster.
 Educated guesses.

12
 Forecasting Techniques
Quantitative Methods
Used when situation is ‘stable’ and historical data exist.
 Existing products
 Current technology
Involves mathematical techniques or mathematical modeling.
Example
Forecasting sales of color televisions.
 Commodity products that are sold every day.

13
 Qualitative Approaches to
Forecasting
 Delphi Approach
 A panel of experts, each of whom is physically
separated from the others and is anonymous, is asked
to respond to a sequential series of questionnaires.
 Requires one person to administer and coordinate the
process and poll the team members (respondents)
through a series of sequential questionnaires.
 After each questionnaire, the responses are tabulated
and the information and opinions of the entire group are
made known to each of the other panel members so
that they may revise their previous forecast response.
 The process continues until some degree of consensus
is achieved.
Conti…
Typically, the procedure consists of the following steps:
Each expert in the group makes his/her own forecasts
in form of statements
The coordinator collects all group statements and
summarizes them
The coordinator provides this summary and gives
another set of questions to each
 group member including feedback as to the input of
other experts.
The above steps are repeated until a consensus is
reached.
 Qualitative Approaches (continued)
 Executive Opinions/Group Consensus:
The subjective views of executives or experts from sales, production,
finance, purchasing, and administration are averaged to generate a
forecast about future sales.
Consumer Surveys:
Surveys regarding specific consumer purchases.
Surveys may consist of telephone contacts, personal interviews, or
questionnaires as a means of obtaining data.
Sales force composite:
Estimates from individual salespersons are reviewed for
reasonableness, then aggregated.
 Quantitative Approaches to
Forecasting
 Quantitative methods are based on an analysis of historical
data concerning one or more time series.
 A time series is a set of observations measured at successive
points in time or over successive periods of time.
 If the historical data used are restricted to past values of the
series that we are trying to forecast, the procedure is called a
time series method.
 If the historical data used involve other time series that are
believed to be related to the time series that we are trying to
forecast, the procedure is called a causal method.
 Quantitative approaches are generally preferred. In this chapter
we will focus on quantitative approaches to forecasting.
Quantitative Forecasting Methods

Quantitative
Forecasting

Time Series Regression

Models Models

2. Moving 3. Exponential
1. Naive
Average Smoothing
a) simple a) level
b) weighted b) trend
c) seasonality
 Time Series Patterns

Components of a Time Series

Historic data may exhibit one of the following pattern:

Level (long-term average) – data fluctuates around a constant mean.

Trend – data exhibits an increasing or decreasing pattern.

Seasonality – effects are similar variations occurring during

corresponding periods, can be quarterly, monthly, weekly, daily, or
even hourly indexes.
Cycle – are the long-term swings about the trend line.
Time Series Patterns
Components of a Time Series
 The trend component accounts for the gradual shifting
of the time series over a long period of time.
 Any regular pattern of sequences of values above and
below the trend line is attributable to the cyclical
component of the series.
 The seasonal component of the series accounts for
regular patterns of variability within certain time periods,
such as over a year.
 The irregular component of the series is caused by
short-term, unanticipated and non-recurring factors that
affect the values of the time series. One cannot attempt
to predict its impact on the time series in advance.
Time Series Models

 Try to predict the future based on past

data
 Assume that factors influencing the past will
continue to influence the future
Random Trend

Seasonal Composite
Product Demand over Time
Demand for product or service

Year Year Year Year

1 2 3 4
Product Demand over Time
Trend component
Seasonal peaks
Demand for product or service

Actual demand
Random line
variation
Year Year Year Year
1 2 3 4
Now let’s look at some time series approaches to forecasting…
Time Series Models

 Time Series : a set of observations measured at

successive times or over successive periods.

 Naïve or Projection

 Simple Moving Average

 Weighted Moving Average

 Exponential Smoothing
1. Naive Approach

 Demand in next period is the

same as demand in most
recent period June forecast = 48
 May sales = 48 →
 The forecast for the period t, Ft, is
simply a projection of previous period
t-1 demand, At-1.
 This method, although easy to use, doesn’t
make use of data and it is easily available to
most managers.
 Usually not good Ft = At-1
2a. Simple Moving Average

 Assumes an average is a good estimator of future behavior

 An n-period moving average uses the last n periods of
demand as a forecast for next periods demand:
 Used if little or no trend
 Used for smoothing
AAt t ++AAt -t1-1++AAt -t 2-2 ++...
...++AAt -t n-n11
FFt t 11 ==
nn

Ft+1 = Forecast for the upcoming period, t+1

n = Number of periods to be averaged
At = Actual occurrence in period t
 Simple moving average
Example: You’re manager in Amazon’s electronics department. You want to
forecast ipod sales for months 4-6 using a 3-period moving average.

Period Actual shed sales 3-month moving average

January 10  
February 12  
March 13  
April 16  
May 19  
june 23  
july 26  
august 30  
september 28  
october 18  
november 16  
december 14  
January    
 Time Series Model
Solution:
2b. Weighted Moving Average
 Gives more emphasis to recent data

FFtt11 == w
w11A
Att ++ w
w22A
Att-1-1 ++w
w33A
Att--22 ++...
...++w
wnnA
Att--nn11
 Weights
decrease for older data
sum to 1.0 Simple
Simple moving
moving
average
average models
models
weight
weight all
all
 the most recent data is the most relevant.
previous
previous
periods
periods equally
equally
 FFt t 11 ==ww11AAt t ++ww22AAt -t1-1++ww33AAt -t2-2++......++wwnnAAt -tn-n11
2b. Weighted Moving Average: 3/6, 2/6, 1/6

Month Sales Weighted

(000) Moving
Average
1 4 NA
2 6 NA
3 5 NA
4 ? 31/6 = 5.167
5 ?
6 ?
 FFt t 11 ==ww11AAt t ++ww22AAt -t1-1++ww33AAt -t2-2++......++wwnnAAt -tn-n11
2b. Weighted Moving Average: 3/6, 2/6, 1/6

Month Sales Weighted

(000) Moving
Average
1 4 NA
2 6 NA
3 5 NA
4 3 31/6 = 5.167
5 7 25/6 = 4.167
6 32/6 = 5.333
3a. Exponential Smoothing
Need
Need
 Assumes the most recent observations haveinitia
initia
ll
the highest predictive value forecast
forecast
 gives more weight to recent time periods FFt
t
to
tostart.
(A
start.
FFt+1
t+1
=
= F
Ftt
+
+ (Att
-
- F
F t)
t)
et
Ft+1 = Forecast value for time t+1
At = Actual value at time t
 = Smoothing constant
Time Series Model

35
3a. Exponential Smoothing – Example 1
FFt+1
t+1
=
= F
Ftt
+
+ (A
(Att
-
- F
Ft )
t)
i Ai
Week Demand
1 820 Given
Given the
the weekly
weekly demand
demand
2 775 data
data what
what are
are the
the exponential
exponential
3 680 smoothing
smoothing forecasts
forecasts for
for
4 655 periods
periods 2-10 using =0.10?
2-10 using =0.10?
5 750
6 802 Assume
Assume FF11=D
=D11
7 798
8 689
9 775
10
3a. Exponential Smoothing – Example 1
FFt+1
t+1
=
= F
Ftt
+
+ (A
(Att
-
- F
Ft )
t)
i Ai Fi
Week Demand  = 0.1 0.6
1 820 820.00 820.00
2 775 820.00 820.00
3 680 F2815.50
= F1+ (A793.00
1–F1) =820+(820–820)
4 655 801.95 725.20=820
5 750 787.26 683.08
6 802 783.53 723.23
7 798 785.38 770.49
8 689 786.64 787.00
9 775 776.88 728.20
10 776.69 756.28
3a. Exponential Smoothing – Example 1
FFt+1
t+1
=
= F
Ftt
+
+ (A
(Att
-
- F
Ft )
t)
i Ai Fi
Week Demand  = 0.1 0.6
1 820 820.00 820.00
2 775 820.00 820.00
3 680 815.50 793.00
F3 = F2+ (A2–F2) =820+(775–820)
4 655 801.95 725.20
5 750 787.26 683.08=815.5
6 802 783.53 723.23
7 798 785.38 770.49
8 689 786.64 787.00
9 775 776.88 728.20
10 776.69 756.28
3a. Exponential Smoothing – Example 1
FFt+1
t+1
=
= F
Ftt
+
+ (A
(Att
-
- F
Ft )
t)
i Ai Fi
Week Demand  = 0.1 0.6
1 820 820.00 820.00
2 775 820.00 820.00
3 680 815.50 793.00
4 655 801.95 725.20
5 750 787.26 683.08
6 802 783.53 723.23This process
7 798 785.38 770.49 continues
8 689 786.64 787.00
through week 10
9 775 776.88 728.20
10 776.69 756.28
3a. Exponential Smoothing – Example 1
FFt+1
t+1
=
= F
Ftt
+
+ (A
(Att
-
- F
Ft )
t)
i Ai Fi
Week Demand  = 0.1  = 0.6
1 820 820.00 820.00
2 775 820.00 820.00
3 680 815.50 793.00
4 655 801.95 725.20
5 750 787.26 683.08 What if the
6 802 783.53 723.23  constant
7 798 785.38 770.49 equals 0.6
8 689 786.64 787.00
9 775 776.88 728.20
10 776.69 756.28
3a. Exponential Smoothing – Example 2
FFt+1
t+1
=
= F
Ftt
+
+ (A
(Att
-
- F
Ft )
t)
i Ai Fi
Month Demand  = 0.3  = 0.6
January 120 100.00 100.00
February 90 106.00 112.00
March 101 101.20 98.80
April 91 101.14 100.12
May 115 98.10 94.65 What if the
June 83 103.17 106.86  constant
July 97.12 92.54 equals 0.6
August
September
 3a. Exponential Smoothing – Example 3

Company
Company A, A, aa personal
personal computer
computer producer
producer
purchases
purchases generic
generic parts
parts and
and assembles
assembles themthem toto
final
final product.
product. Even
Even though
though mostmost ofof the
the orders
orders
require
require customization,
customization, they
they have
have many
many common
common
components.
components. Thus,
Thus, managers
managers of of Company
Company A A need
need
aa good
good forecast
forecast ofof demand
demand so so that
that they
they can
can
purchase
purchase computer
computer parts
parts accordingly
accordingly to to minimize
minimize
inventory
inventory cost
cost while
while meeting
meeting acceptable
acceptable service
service
level.
level. Demand
Demand datadata for
for its
its computers
computers for for the
the past
past 55
months
months isis given
given in
in the
the following table..
following table
3a. Exponential Smoothing – Example 3
FFt+1
t+1
=
= F
Ftt
+
+ (A
(Att
-
- F
Ft )
t)
i Ai Fi
Month Demand  = 0.3  = 0.5
January 80 84.00 84.00
February 84 82.80 82.00
March 82 83.16 83.00
April 85 82.81 82.50
May 89 83.47 83.75 What if the
June 85.13 86.38  constant
July ?? ?? equals 0.5
Forecast Effects of
Smoothing Constant 
Ft+1 = Ft +  (At - Ft)
or Ft+1 =  At + (1- ) At - 1 + (1- )2At - 2 + ...
w1 w2 w3

Weights
= Prior Period 2 periods ago 3 periods ago
 (1 - ) (1 - )2

= 0.10
10% 9% 8.1%

 = 0.90 90% 9% may be 0.9%

Several values of the smoothing constant tried, and the
one with the lowest MAD could be selected.
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

• Different models for 3 month vs. 10 years

4. Presence of data patterns
To Use a Forecasting Method

 Collect historical data

 Select a model
 Moving average methods
 Select n (number of periods)
 For weighted moving average: select weights
 Exponential smoothing
 Select 
 Selections should produce a good forecast
…but what is a good forecast?
A good forecast Has a small error.
Error = Demand - Forecast
 Selecting the Right Forecasting Model

Forecasting during product life cycle

Measures of Forecast Error
et
nn

a. MAD = Mean Absolute Deviation 

 AA --FF
t=1
tt tt

 Measures the total error in a forecast without regard

MAD
MAD== t=1
nn
to sign

b. Cumulative Forecast Error (CFE)

Also called running sum of forecast error (RSFE)
CFE    actual  forecast 
Measures any bias in the forecast
nn

c. MSE = Mean Squared Error   A - F 

  At t - Ft t 
22

t=
t =11
MSE =
MSE =
 Penalizes larger errors nn
d. RMSE = Root Mean Squared Error RMSE
RMSE == MSE
MSE
 Ideal values =0 (i.e., no forecasting error)
 nn

MAD Example 
 AA --FF
t=1
tt tt = 40 =10
MAD
MAD== t=1 4
nn

What
What isis the
the MAD
MAD value
value given
given the
the
forecast
forecast values
values in
in the
the table
table below?
below?
At Ft
Month Sales Forecast |At – Ft|
1 220 n/a
2 250 255 5
3 210 205 5
4 300 320 20
5 325 315 10
= 40
 nn

  A - F 
  At t - Ft t 
22

= 550 =137.5
MSE/RMSE Example MSE =
MSE =
t =t =11

nn 4

What
What isis the
the MSE
MSE value?
value? RMSE = √137.5
=11.73
At Ft
Month Sales Forecast |At – Ft| (At – Ft)2
1 220 n/a
2 250 255 5 25
3 210 205 5 25
4 300 320 20 400
5 325 315 10 100
= 550
 Measures of Error

1. Mean Absolute Deviation

t At Ft et |et| et2 (MAD)
n

e t
84
Jan 120 100 20 20 400 MAD  1 = 14
n
6
Feb 90 106 -16 16 256
2a. Mean Squared Error
Mar 101 102 -1 1 1 (MSE)
n

April 91 101 -10 10 100 

 te  2

MSE  1 1,446
May 115 98 17 17 289 n = 241
6
June 83 103 -20 20 400
2b. Root Mean Squared Error
(RMSE)
-10 84 1,446
An accurate forecasting system will have small MAD, MSE and RMSE  MSE
RMSE; ideally equal to zero. A large error may indicate that either
the forecasting method used or the parameters such as α used in = SQRT(241)
the method are wrong.
Note: In the above, n is the number of periods, which is 6 in our
=15.52
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.

 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!

Measuring Forecast Accuracy and Error

Example:
Weighted (n=3,
Simple t-1=0.45, Exponential Exponential Exponential
No Actual Naïve
(n=3) t-2=0.35, (α=0.1) (α=0.5) (α=0.8)
t-3=0.2)
1 110     105 105 105
2 100
3 120
4 140
5 170
6 150
7 160
8 190
9 200
10 190
11  
MAD
CFE
RMSE
TS
Measuring Forecast Accuracy and Error
 Regression Analysis as a Method for
Forecasting
 Regression analysis takes advantage of the relationship between two
variables.
 Demand is then forecasted based on the knowledge of this relationship and
for the given value of the related variable.
Ex: Sale of Tires (Y), Sale of Autos (X) are obviously related
If we analyze the past data of these two variables and establish a relationship
between them, we may use that relationship to forecast the sales of tires
given the sales of automobiles.
The simplest form of the relationship is, of course, linear, hence it is referred to as
a regression line.

Sales of Autos (100,000)

 Formulas
yy == aa ++ bb xx

where,
where,


x

xy  n x y
y
b
 x  nx 2 2

x
y
a  y  bx
Regression – Example: find F(July)

 xy  n x y a  y  bx
yy == aa++ bb X
X b
 x  nx
2 2

MonthAdvertising Sales X 2 XY
January 3 1 9.00 3.00
February 4 2 16.00 8.00
March 2 1 4.00 2.00
April 5 3 25.00 15.00
May 4 2 16.00 8.00
June 2 1 4.00 2.00
July

TOTAL 20 10 74 38

y= a + bx
Solution ( Demand forecast for Jul)
2 Sales Demand      
Month x y xy x^2 y^2
JAN 3 1 3 9 1
FEB 4 2 8 16 4
MAR 2 1 2 4 1
APR 5 3 15 25 9
MAY 4 2 8 16 4
JUN 2 1 2 4 1
sum 20 10 38 74 20
JUL 6 ????      
xbar ybar
b = 0. 64 3.333 1.8
   

a = - 0. 46 y= a + bx
y= - 0.46 + 0.64 x
y (Jul) = 3.38
Thank you!!!