Operations Management 1 – Chapter 4 – Handouts 1

OPERATIONS MANAGEMENT 1 – HANDOUTS No 4

Chapter 4 - FORECASTING

1. What is Forecasting?

 Process of predicting future events

 Underlying basis of all business decisions
 Production
 Inventory
 Personnel
 Facilities

2. Forecasting Time Horizons

There are 3 categories of Time Horizons:

 Short-range forecast
 Up to 1 year, generally less than 3 months
 Purchasing, job scheduling, workforce levels, job assignments, production levels
 Medium-range forecast
 3 months to 3 years
 Sales and production planning, budgeting
 Long-range forecast
 3+ years
 New product planning, facility location, research and development

How do medium and long-range forecast differ from short-range forecast?

They differ by three features:

(1) Intermediate (medium) and long-range forecasts deal with more comprehensive issues and
support management decisions regarding planning and products, plants, and processes.
(2) Short-term forecasting usually employs different methodologies than longer-term
forecasting.
(3) Short-term forecasts tend to be more accurate than longer forecasts because factors that
influence demand change every day.

3. Types of Forecasts

We have the following types of forecast:

 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 products and services

Compiled by Sambil M. Page 1 of 10

Operations Management 1 – Chapter 4 – Handouts 1
4. Steps in the forecasting system

5. Forecasting Approaches

There are two types of forecasting approaches:

A. Qualitative Methods
 Used when situation is vague and little data exist
 Forecasting new products, new technology
 Involves intuition, experience
 e.g., forecasting sales on Internet

B. Quantitative Methods
 Used when situation is ‘stable’ and historical data exist
 Forecasting existing products, current technology
 Involves mathematical techniques
 e.g., forecasting sales of color televisions

5.1 Overview of Qualitative Methods

Qualitative forecasting methods include:

 Jury of executive opinion
 Pool opinions of high-level experts, sometimes augment by statistical models
 Involves small group of high-level experts and managers
 Group estimates demand by working together
 Combines managerial experience with statistical models
 Relatively quick
 ‘Group-think’
disadvantage

 Delphi method
 Panel of experts, queried iteratively
 Iterative group process, continues until consensus is reached
 3 types of participants
 Decision makers
 Staff
 Respondents

 Sales force composite

 Estimates from individual salespersons are reviewed for reasonableness, then
aggregated
 Each salesperson projects his or her sales

Compiled by Sambil M. Page 2 of 10

Operations Management 1 – Chapter 4 – Handouts 1
 Combined at district and national levels
 Sales reps know customers’ wants
 Tends to be overly optimistic

 Consumer Market Survey

 Ask the customer
 Ask customers about purchasing plans
 What consumers say, and what they actually do are often different
 Sometimes difficult to answer

Overview of Quantitative Approaches

Time Series Forecasting

 Set of evenly spaced numerical data
 Obtained by observing response variable at regular time periods
 Forecast based only on past values, no other variables important
 Assumes that factors influencing past and present will continue influence in future

Time Series Components

Compiled by Sambil M. Page 3 of 10

Operations Management 1 – Chapter 4 – Handouts 1
Trend Component
 Persistent, overall upward or downward pattern
 Changes due to population, technology, age, culture, etc.
 Typically several years duration

Seasonal Component
 Regular pattern of up and down fluctuations
 Due to weather, customs, etc.
 Occurs within a single year

Cyclical Component
 Repeating up and down movements
 Affected by business cycle, political, and economic factors
 Multiple years duration
 Often causal or associative relationships

Random Component
 Erratic, unsystematic, ‘residual’ fluctuations
 Due to random variation or unforeseen events
 Short duration and no repeating

Naive Approach

 Assumes demand in next

period is the same as
demand in most recent period
 e.g., If January sales were 68, then February sales will be 68
 Sometimes cost effective and efficient
 Can be good starting point

Moving Average Method

 MA is a series of arithmetic means

 Used if little or no trend
 Used often for smoothing
 Provides overall impression of data over time

Compiled by Sambil M. Page 4 of 10

Operations Management 1 – Chapter 4 – Handouts 1

Moving Average Example

Donna’s Garden Supply wants a 3-month moving average forecast

Approach: Storage shed are shown in the middle column of the table below. The 3-month
moving average is shown on the right.

Weighted Moving Average

 Used when trend is present

 Older data usually less important
 Weights based on experience and intuition

Weighted Moving Average Example

Donna’s Garden Supply (See the first example) wants to forecast storage shed sales by weighting
the past 3 months, with more given to recent data to make them more significant.

Approach: Assign more weight to recent data as follows:

Forecast this month =

3 x Sales last month + 2 x Sales 2 months ago + 1 x Sales 3 months ago
Sum of the weights

Potential Problems With Moving Average

 Increasing n smoothes the forecast but makes it less sensitive to changes
 Do not forecast trends well
 Require extensive historical data
Compiled by Sambil M. Page 5 of 10
Operations Management 1 – Chapter 4 – Handouts 1
Exponential Smoothing

 Form of weighted moving average

 Weights decline exponentially
 Most recent data weighted most
 Requires smoothing constant (a)
 Ranges from 0 to 1
 Subjectively chosen
 Involves little record keeping of past data

New forecast = Last period’s forecast + α (Last period’s actual demand – Last period’s forecast)

Ft = Ft – 1 + α (At – 1 - Ft – 1)

Where Ft = new forecast

Ft – 1 = previous forecast
a = smoothing (or weighting)
constant (0 ≤ a ≤ 1)

Exponential Smoothing Example

In January, a car dealer predicted February demand for 142 Ford Mustangs. Actual February
demand was 153 autos. Using a smoothing constant chosen by management of α = 0.20, the dealer
wants to forecast March demand using the exponential smoothing model.

Approach: The formula introduced above can be applied

Predicted demand = 142 Ford Mustangs

Actual demand = 153
Smoothing constant a = .20

Common Measures of Error

Determining the Mean Absolute Deviation (MAD)

During the past 8 quarters, the Port of Baltimore has unloaded large quantities of grain from ships.
The port’s operations manager wants to test the use of exponential smoothing to see how well the
technique works in predicting tonnage unloaded. He guesses that the forecast of grain unloaded in
the first quarter was 175 tons. Two values of α are to be examined: α = 0.10 and α = 0.50

Approach: Compare the actual data with the data we forecast (using each of the two α values)
and then find the absolute deviation and MADs

Compiled by Sambil M. Page 6 of 10

Operations Management 1 – Chapter 4 – Handouts 1
Solution: The table below shows the detailed calculations for α = 0.10 only

Actual
Forecast Forecast
Quarter Tonnage
with α = 0.10 with α = 0.50
Unloaded
1 180 175 175
2 168 175.50 = 175.00 + 0.10(180 – 175) 177.50
3 159 174.75 = 175.50 + 0.10(168 – 175.50) 172.75
4 175 173.18 = 174.75 + 0.10(159 – 174.75) 165.88
5 190 173.36 = 173.18 + 0.10(175 – 173.18) 170.44
6 205 175.02 = 173.36 + 0.10(190 – 173.36) 180.22
7 180 178.02 = 175.02 + 0.10(205 – 175.02) 192.61
8 182 178.22 = 178.02 + 0.10(180 – 178.02) 186.30
9 ? 178.59 = 178.22 + 0.10(182 – 178.22) 184.15

Based on the calculations, it is advisable to perform forecasts using α = 0.10, because the MAD of
the forecast with α = 0.10 is the smallest.

Compiled by Sambil M. Page 7 of 10

Operations Management 1 – Chapter 4 – Handouts 1
Practice Problems: Chapter 4, Forecasting

Problem 1:
Auto sales at Carmen’s Chevrolet are shown below. Develop a 3-week moving average.

Week Auto
Sales

1 8

2 10

3 9

4 11

5 10

6 13

7 -

Problem 2:
Carmen’s decides to forecast auto sales by weighting the three weeks as follows:

Weights Period
Applied

3 Last week

2 Two weeks ago

1 Three weeks ago

6 Total
Problem 3:
A firm uses simple exponential smoothing with α = 0.1 to forecast demand. The forecast for the
week of January 1 was 500 units whereas the actual demand turned out to be 450 units. Calculate
the demand forecast for the week of January 8.

Problem 4:
Exponential smoothing is used to forecast automobile battery sales. Two value of α are examined,
α = 0.8 and α = 0.5. Evaluate the accuracy of each smoothing constant. Which is preferable?
(Assume the forecast for January was 22 batteries.) Actual sales are given below:

Month January February March April May June

Actual Battery Sales 20 21 15 14 13 16

Forecast 22

Compiled by Sambil M. Page 8 of 10

Operations Management 1 – Chapter 4 – Handouts 1
ANSWERS:

Problem 1:

Moving average =
∑ demand in previous n periods
n

Week Auto Three-Week Moving

Sales Average

1 8

2 10

3 9

4 11 (8 + 9 + 10) / 3 = 9

5 10 (10 + 9 + 11) / 3 = 10

6 13 (9 + 11 + 10) / 3 = 10

7 - (11 + 10 + 13) / 3 = 11
1/3

Problem 2:

Weighted moving average =

∑ (weight for period n)(demand in period n)
∑ weights
Week Auto Three-Week Moving Average
Sales

1 8

2 10

3 9

4 11 [(3*9) + (2*10) + (1*8)] / 6 = 9 1/6

5 10 [(3*11) + (2*9) + (1*10)] / 6 = 10 1/6

6 13 [(3*10) + (2*11) + (1*9)] / 6 = 10 1/6

7 - [(3*13) + (2*10) + (1*11)] / 6 = 11 2/3

Problem 3:
Ft = Ft −1 + α ( A t −1 − Ft −1 ) = 500 + 0.1( 450 − 500) = 495 units

Compiled by Sambil M. Page 9 of 10

Operations Management 1 – Chapter 4 – Handouts 1
Problem 4:

Month Actual Battery Rounded Absolute Rounded Absolute

Sales Forecast with Deviation Forecast Deviation
a =0.8 with a =0.8 with a =0.5 with a =0.5

January 20 22 2 22 2

February 21 20 1 21 0

March 15 21 6 21 6

April 14 16 2 18 4

May 13 14 1 16 3

June 16 13 3 14.5 1.5

S = 15 S = 16

2.56 2.95

SE 3.5 3.9

On the basis of this analysis, a smoothing constant of a = 0.8 is preferred to that of a = 0.5 because
it has a smaller MAD.

Compiled by Sambil M. Page 10 of 10