Business Analytics: Methods, Models,

and Decisions
Third Edition

Chapter 9
Forecasting
Techniques

Copyright © 2020, 2016, 2013 Pearson Education, Inc. All Rights Reserved Slide - 1
Forecasting Techniques
• Managers require good forecasts of future events.
• Business Analysts may choose from a wide range of
forecasting techniques to support decision making.
• Three major categories of forecasting approaches:

1. Qualitative and judgmental techniques

2. Statistical time-series models
3. Explanatory/causal models

Copyright © 2020, 2016, 2013 Pearson Education, Inc. All Rights Reserved Slide - 2
Qualitative and Judgmental
Forecasting
• Qualitative and Judgmental techniques rely on experience and intuition.

• They are necessary when historical data is not available or when predictions are needed
far into the future.

• The historical analogy approach obtains a forecast through comparative analysis with
prior situations.

• The Delphi method questions an anonymous panel of experts 2-3 times in order to
reach a convergence of opinion on the forecasted variable.

• Sales force polling- known as opinion poll method. Each sales representative,
profesisonal experts , the market consultant are asked to estimate their sales- company
will revise and formulate future forecast

• Customer Survey- Collect opinion from all customer or potential customers

Copyright © 2020, 2016, 2013 Pearson Education, Inc. All Rights Reserved Slide - 3
Example 9.1: Predicting the Price of
Oil
• Early 1988 – oil price was about $22 a barrel
• Mid-1988 – oil price dropped to $11 a barrel because
of oversupply, high production in non-OPEC regions,
and lower than normal demand
• In the past, OPEC would raise the price of oil.
• Historical analogy would forecast a higher price.
• However, the price continued to drop even though
OP EC agreed to cut production.
P

• Historical analogies cannot always account for

current realities!
Copyright © 2020, 2016, 2013 Pearson Education, Inc. All Rights Reserved Slide - 4
Indicators and Indexes
• Indicators are measures that are believed to
influence the behavior of a variable we wish to
forecast.
• Indicators are often combined quantitatively into an
index, a single measure that weights multiple
indicators, thus providing a measure of overall
expectation.
– Example: Dow Jones Industrial Average (DJIA)

Copyright © 2020, 2016, 2013 Pearson Education, Inc. All Rights Reserved Slide - 5
Example 9.2: Economic Indicators
• GDP (Gross Domestic Product) measures the value of all
goods and services produced.
– GDP rises and falls in a cyclic fashion.
• Forecasting GDP is often done using leading indicators
(series that change before the GDP changes) and lagging
indicators (series that follow changes in the GDP) indicators.
• Examples
Leading – formation of business enterprises
– percent change in money supply (M1)
Lagging – business investment expenditures
– prime rate
– inventories on hand
Copyright © 2020, 2016, 2013 Pearson Education, Inc. All Rights Reserved Slide - 6
Example 9.3: Leading Economic
Indicators
• An Index of Leading Indicators was developed by
the Department of Commerce.
• This index is related to the economic performance is
available from [Link].
• It includes measures such as:
– average weekly manufacturing hours
– new orders for consumer goods
– building permits for private housing
– S&P 500 stock prices

Copyright © 2020, 2016, 2013 Pearson Education, Inc. All Rights Reserved Slide - 7
Statistical Forecasting Models
• Time Series – a stream of historical data, such as weekly
sales
– T = number of periods,
• Time series generally have components such as:
– random behavior
– trends (upward or downward)
– seasonal effects
– cyclical effects
• Stationary time series have only random behavior.
• A trend is a gradual upward or downward movement of
a time series.
Copyright © 2020, 2016, 2013 Pearson Education, Inc. All Rights Reserved Slide - 8
Example 9.4: Identifying Trends in a
Time Series
• Total Energy Production & Consumption
– General upward trend with some short downward trends;
the time series is composed of several different short trends.

Copyright © 2020, 2016, 2013 Pearson Education, Inc. All Rights Reserved Slide - 9
Seasonal Effects
• A seasonal effect is one that repeats at fixed
intervals of time, typically a year, month, week, or
day.

Copyright © 2020, 2016, 2013 Pearson Education, Inc. All Rights Reserved Slide - 10
Cyclical Effects
• Cyclical effects describe ups and downs over a
much longer time frame, such as several years.

Copyright © 2020, 2016, 2013 Pearson Education, Inc. All Rights Reserved Slide - 11
Forecasting Models for Stationary
Time Series
• Moving average model
• Exponential smoothing model
– These are useful over short time periods when trend, seasonal, or
cyclical effects are not significant.
Differences
- Moving average is used when demand has no observable trend
or seasonality. When dealing with moving average, the forecast
for future periods are the same. Moving average is based used
when dealing with stationary time series that has a continuous
change over time.
- Exponential smoothing is appropriate when demand has no
observable trend or seasonality. Each level is weighted differently
in which older observations are weighted lower than newer
observations.
Copyright © 2020, 2016, 2013 Pearson Education, Inc. All Rights Reserved Slide - 12
Moving Average Models
• The simple moving average method is a smoothing method based on the
idea of averaging random fluctuations in the time series to identify the
underlying direction in which the time series is changing.
• Refer to video :
• [Link]

• The simple moving average forecast for the next period is computed as the
average of the most recent k observations.

– Larger values of k result in smoother forecast models since

extreme values have less impact.

Copyright © 2020, 2016, 2013 Pearson Education, Inc. All Rights Reserved Slide - 13
Example 9.5: Moving Average
Forecasting
• The Tablet Computer Sales file contains the number of
units sold over the past 17 weeks.

• Three-period moving average forecast for week 18:

Copyright © 2020, 2016, 2013 Pearson Education, Inc. All Rights Reserved Slide - 14
Spreadsheet Implementation of
Moving Average Forecasting

Copyright © 2020, 2016, 2013 Pearson Education, Inc. All Rights Reserved Slide - 15
Example 9.6: Using Excel’s Moving
Average Tool
• Data Analysis options

We do not recommend
using the chart or error
options because the
forecasts generated
by this tool are not
properly aligned with
the data.

Copyright © 2020, 2016, 2013 Pearson Education, Inc. All Rights Reserved Slide - 16
 The formula numbers need to be
changed to 9.2 through 9.5. I don’t
have the software to edit this

Error Metrics and Forecast Accuarcy

• Mean absolute deviation
(MAD)

• Mean square error (MSE)

• Root mean square error

(RMSE)

• Mean absolute percentage

error (MAPE)

Copyright © 2020, 2016, 2013 Pearson Education, Inc. All Rights Reserved Slide - 17
Example 9.7: Using Error Metrics to
Compare Moving Average Forecasts
• Tablet Computer Sales data
• 2-, 3-, and 4-period moving average models
• 2-period model has lowest error metric values.

Copyright © 2020, 2016, 2013 Pearson Education, Inc. All Rights Reserved Slide - 18
Exponential Smoothing Models
• Simple exponential smoothing model:
The formula number needs to be
changed to 9.6. I don’t have the
software to edit this

where is the forecast for time period is the

forecast for period t, is the observed value in period t,
and α is a constant between 0 and 1 called the smoothing
constant.
• To begin, set equal to the actual observation in
period 1,
Copyright © 2020, 2016, 2013 Pearson Education, Inc. All Rights Reserved Slide - 19
Example 9.8: Using Exponential Smoothing
to Forecast Tablet Computer Sales

Forecast for week 3 when

Copyright © 2020, 2016, 2013 Pearson Education, Inc. All Rights Reserved Slide - 20
Example 9.9: Finding the Best Exponential
Smoothing Model for Tablet Computer Sales

The forecast using provides the lowest error metrics.

Copyright © 2020, 2016, 2013 Pearson Education, Inc. All Rights Reserved Slide - 21
Example 9.10: Using Excel’s Exponential
Smoothing Tool
• REFER TO VIDEO
[Link]
• Select Data Analysis from the Analysis group and then
choose Exponential Smoothing.
• Note that Damping factor = 1−α
• The first cell of the Output Range should be adjacent to the
first data point.

Copyright © 2020, 2016, 2013 Pearson Education, Inc. All Rights Reserved Slide - 22
Example 9.10 Continued
• Exponential Smoothing tool results

Copyright © 2020, 2016, 2013 Pearson Education, Inc. All Rights Reserved Slide - 23
Forecasting Models for Time Series
with a Linear Trend
• Double moving average and double exponential
smoothing The formula number needs to be
changed to 9.7. I don’t have the
• Based on the linear trend equation software to edit this

• The forecast for k periods into the future is a function of

the level and the trend .
• The models differ in their computations of .

Copyright © 2020, 2016, 2013 Pearson Education, Inc. All Rights Reserved Slide - 24
Double Exponential Smoothing
• Estimates of the parameters are obtained from the
following equations:

• Initial values are chosen for and

Equation (9.8) must then be used to compute
for the entire time series to be able to generate
forecasts into the future. The forecast for k periods
beyond the last period (period T) is

Copyright © 2020, 2016, 2013 Pearson Education, Inc. All Rights Reserved Slide - 25
Example 9.11: Double Exponential
Smoothing
• First ten years of data in the Excel file Coal Production
• Choose  = 0.6 and  = 0.4
– See text for computational details.

Copyright © 2020, 2016, 2013 Pearson Education, Inc. All Rights Reserved Slide - 26
Regression-Based Forecasting for
Time Series with a Linear Trend
• Simple linear regression can be applied to
forecasting using time as the independent variable.

Copyright © 2020, 2016, 2013 Pearson Education, Inc. All Rights Reserved Slide - 27
Example 9.12: Forecasting Using
Trendlines
• Coal Production data with a linear trendline

Note that the linear

model does not
adequately predict the
recent drop in
production after 2008.

Copyright © 2020, 2016, 2013 Pearson Education, Inc. All Rights Reserved Slide - 28
Autocorrelation in Time Series
• When autocorrelation is present, successive observations
are correlated with one another; for example, large
observations tend to follow other large observations, and
small observations also tend to follow one another.
– In such cases, other approaches, called autoregressive models,
are more appropriate.

Copyright © 2020, 2016, 2013 Pearson Education, Inc. All Rights Reserved Slide - 29
Forecasting Time Series with
Seasonality
• When time series exhibit seasonality, different
techniques provide better forecasts than the ones
we have described:
– Multiple regression models with categorical variables for
the seasonal components
– Holt-Winters models, similar to exponential smoothing
models in that smoothing constants are used to smooth
out variations in the level and seasonal patterns over
time.

Copyright © 2020, 2016, 2013 Pearson Education, Inc. All Rights Reserved Slide - 30
Example 9.13: Regression-Based
Forecasting for Natural Gas Usage
• Gas & Electric Excel file
• Use a seasonal categorical
variable with k = 12 levels.
• Construct the regression
model using k − 1 dummy
variables, with January
being the reference month.

Copyright © 2020, 2016, 2013 Pearson Education, Inc. All Rights Reserved Slide - 31
Example 9.13 Continued
• Data matrix

Copyright © 2020, 2016, 2013 Pearson Education, Inc. All Rights Reserved Slide - 32
Example 9.13 Continued
• Final regression
results (time and
February were
insignificant)

Copyright © 2020, 2016, 2013 Pearson Education, Inc. All Rights Reserved Slide - 33
Holt-Winters Models for Forecasting Time
Series with Seasonality and No Trend
• The Holt-Winters additive seasonality model with no trend applies
to time series with relatively stable seasonality and is based on the
equation

• The Holt-Winters multiplicative seasonality model with no trend

applies to time series whose amplitude increases or decreases over
time and is

A chart of the time series should be viewed first to identify the

appropriate type of model to use.

Copyright © 2020, 2016, 2013 Pearson Education, Inc. All Rights Reserved Slide - 34
Holt-Winters Additive Seasonality
Model with No Trend

• The level and seasonal factors are estimated as

• The forecast for the next period is

Copyright © 2020, 2016, 2013 Pearson Education, Inc. All Rights Reserved Slide - 35
Holt-Winters Additive Seasonality
Model with No Trend

• Estimate the level and seasonal factors for the

first s periods (that is, the length of a season)

• Then we use the smoothing equations to update

at and St and calculate forecasts.

Copyright © 2020, 2016, 2013 Pearson Education, Inc. All Rights Reserved Slide - 36
Example 9.14: Using the Holt-Winters
Additive Seasonality Model with No Trend
• Data for gas usage in the Excel file Gas & Electric
• Arbitrarily select  = 0.4 and  = 0.9.
– See the text for computational details.

Copyright © 2020, 2016, 2013 Pearson Education, Inc. All Rights Reserved Slide - 37
Holt-Winters Multiplicative
Seasonality Model with No Trend

• The multiplicative seasonal model has the same

basic smoothing structure as the additive
seasonal model with some key differences:

• The forecast for the next period is

Copyright © 2020, 2016, 2013 Pearson Education, Inc. All Rights Reserved Slide - 38
Holt-Winters Multiplicative
Seasonality Model with No Trend

• Initialize the values for the level and seasonal

factors:

• This model can be implemented on a

spreadsheet in a similar fashion as the additive
model.

Copyright © 2020, 2016, 2013 Pearson Education, Inc. All Rights Reserved Slide - 39
Holt-Winters Models for Forecasting
Time Series with Seasonality and Trend
• The Holt-Winters additive model applies to time series with relatively
stable seasonality and is based on the equation

• The Holt-Winters multiplicative model applies to time series whose

amplitude increases or decreases over time and is

• A chart of the time series should be viewed first to identify the

appropriate type of model to use. The formula numbers need to be
changed to 9.17 and 9.18. I don’t
have the software to edit this

Copyright © 2020, 2016, 2013 Pearson Education, Inc. All Rights Reserved Slide - 40
Holt-Winters Additive Seasonality Model
with Trend
• This model is similar to the additive model that
incorporates only seasonality, but with the addition of a
trend component:

• The forecast for period t + 1 is

• The forecast for k periods beyond the last period of

observed data (period T) is

Copyright © 2020, 2016, 2013 Pearson Education, Inc. All Rights Reserved Slide - 41
Holt-Winters Additive Seasonality
Model with Trend

• The initial values for level and seasonal factors

are the same as in the additive seasonality
model without trend, that is, formulas (9.13) and
(9.14).
• The initial values for the trend component are

Copyright © 2020, 2016, 2013 Pearson Education, Inc. All Rights Reserved Slide - 42
Example 9.15: Using the Holt-Winters
Additive Model for Seasonality and Trend
• Excel file New Car Sales
• Stable seasonality and an increasing trend

Copyright © 2020, 2016, 2013 Pearson Education, Inc. All Rights Reserved Slide - 43
Example 9.15 Continued
• Arbitrarily select  = 0.3,  = 0.2, and  = 0.9.
– See text for computational details.

Copyright © 2020, 2016, 2013 Pearson Education, Inc. All Rights Reserved Slide - 44
Holt-Winters Multiplicative
Seasonality Model with Trend
• The Holt-Winters multiplicative model is similar to
the additive model for seasonality, but with a
trend component:

Copyright © 2020, 2016, 2013 Pearson Education, Inc. All Rights Reserved Slide - 45
Holt-Winters Multiplicative
Seasonality Model with Trend
• The forecast for period t + 1 is

• The forecast for k periods beyond the last period of

observed data (period T) is

• Initialization is performed in the same way as for the

multiplicative model without trend. The model can be
implemented in a similar fashion on a spreadsheet as the
additive model.

Copyright © 2020, 2016, 2013 Pearson Education, Inc. All Rights Reserved Slide - 46
Selecting Appropriate Time-Series-
Based Forecasting Methods

Copyright © 2020, 2016, 2013 Pearson Education, Inc. All Rights Reserved Slide - 47
Regression Forecasting with Causal
Variables
• In many forecasting applications, other independent
variables besides time, such as economic indexes
or demographic factors, may influence the time
series.
• Explanatory/causal models, often called
econometric models, seek to identify factors that
explain statistically the patterns observed in the
variable being forecast, usually with regression
analysis.

Copyright © 2020, 2016, 2013 Pearson Education, Inc. All Rights Reserved Slide - 48
Example 9.16: Forecasting Gasoline
Sales Using Simple Linear Regression
• Excel file Gasoline Sales
• Simple trendline using week as the independent variable

Predicted sales for week 11

Copyright © 2020, 2016, 2013 Pearson Education, Inc. All Rights Reserved Slide - 49
Example 9.17: Incorporating Causal Variables in
a Regression-Based Forecasting Model
• The average price per gallon changes each week, and this
may influence consumer sales. Average price per gallon is
a causal variable.
• Develop a multiple linear regression model to predict
gasoline sales using both time and price per gallon.

Copyright © 2020, 2016, 2013 Pearson Education, Inc. All Rights Reserved Slide - 50
Example 9.17 Continued
• Multiple regression model

Predicted sales for week 11

Copyright © 2020, 2016, 2013 Pearson Education, Inc. All Rights Reserved Slide - 51
The Practice of Forecasting
• Judgmental and qualitative methods are used for
forecasting sales of product lines and broad
company and industry forecasts.
• Simple time-series models are used for short- and
medium-range forecasts.
• Regression methods are typically used for long-term
forecasts.

Copyright © 2020, 2016, 2013 Pearson Education, Inc. All Rights Reserved Slide - 52