You are on page 1of 26

Forecasting

Chapter 11

McGraw-Hill/Irwin

The McGraw-Hill Companies, Inc. 2007, All Rights Reserved

Chapter 11 Outline
A Forecasting Framework Qualitative Forecasting Methods Time-Series Forecasting Moving Average Exponential Smoothing Forecast Errors Advanced Time-Series Forecasting Causal Forecasting Methods Selecting a Forecasting Method Collaborative Planning, Forecasting and Replenishment
11-2

A Forecasting Framework
Focus of the chapter is on the forecasting of demand for output from the operations function.
Demand may differ from sales

Difference between forecasting and planning


Forecasting: what we think will happen Planning: what we think should happen

Forecasting application in various decision areas of operations (capacity planning, inventory management, others) Forecasting uses and methods (See Table 11.1)
11-3

Use of Forecasting: Operations Decisions


Time Horizon Process design Capacity planning, facilities Aggregate planning S cheduling Long Accuracy R equired Medium Number of Forecasts Management Forecasting Level Method Qualitative or causal Qualitative and causal Causal and time series Time series Time series

S ingle or few Top

Long

Medium

S ingle or few Top

Medium S hort

High Highest Highest

Few Many Many

Middle Lower Lower

Inventory hort management S

11-4

Use of Forecasting: Marketing & Finance


Time Horizon Long-range marketing programs Pricing decisions Long Accuracy R equired Medium Number of Forecasts Management Forecasting Level Method Qualitative

S ingle or few Top

S hort

High Medium High Highest

Many S ingle Many Few

Middle Top Lower Top

Time series Qualitative and causal Time series Causal and time series

New product introduction Medium Cost estimating Capital budgeting S hort Medium

11-5

Qualitative Forecasting Methods


Based upon managerial judgment when there is a lack of data. No specific model. Major methods:
Delphi Technique Market Surveys Life-cycles Analogy Informed Judgment (nave models)

11-6

Time-Series Forecasting
Components of time-series data:
Trendgeneral direction (up or down) Seasonalityshort term recurring cycles Cyclelong term business cycle Error (random or irregular component)

Decomposition of time-series
Data are broken into the four components

Moving Averages Exponential Smoothing


11-7

Moving Average
Assumes no trend, seasonal or cyclical components. Simple Moving Average:
Dt Dt 1 ...... Dt N 1 At N

Ft 1 At

Weighted Moving Average:


Ft 1 At W1 Dt W2 Dt 1 ...... WN Dt N 1
11-8

Moving Average
Compute three period moving average (number of periods is the decision of the forecaster)

Period
1 2

Actual Demand
10 18

Forecast

3
4 (10+18+29)/3 = 19

29
19

Period 5 will be (18+29+actual for period 4)/3


11-9

Time-Series Data Plot

Note: The more periods, the smoother the forecast.


11-10

Exponential Smoothing
The new average is computed from the old average:

At Dt 1 At 1
The value of the smoothing constant () is a choice. It determines how much the calculation smooths out the random variations. Its value can be set between zero (0) and one (1). Normally it is in the 0.1 to 0.2 range.

11-11

Simple Exponential Smoothing


The forecast: Ft 1 Ft Dt Ft
F=forecast of demand (both this period and next) D = actual demand (this period) t = time period

No trend, cyclical or seasonal components. Note: we are adjusting Ft to get Ft+1


11-12

Exponential Smoothingcalculation
Facts:
September forecast for sales was 15 September actual sales were 13 Alpha ( ) is 0.2 What is the forecast for October?

Calculation
October Forecast = September forecast + (September actual-September forecast) =15+0.2(13-15)=15+0.2(-2)=15-0.4=14.6
11-13

Forecast Errors
Cumulative Sum of Forecast Error (CFE) and Mean Error (ME) Mean Square Error (MSE) Mean Absolute Deviation (MAD)measure of deviation in units. Mean Absolute Percentage Error (MAPE)

Tracking Signal (TS)relative measure of bias


11-14

Forecast Errors: Formulas


Cumulative sum of Forecast Errors

CFE = et
i=1
n

Mean Absolute Percentage Error

MAPE =

| D
i=1

et

| 100

n
n

Mean Square Error

e
MSE =
i=1

2 t

Tracking Signal

e
TS =
i=1

n
Mean Absolute Deviation

MAD

|e |
t

MAD =

i=1

Mean Error

e
ME =
i=1

n
11-15

Tracking Signal
Analogous to control charts in quality control, viz. if there is no bias, its values should fluctuate around zero. Is a relative measure, i.e. the numbers mean the same for any forecast.

11-16

Advanced Time-Series Forecasting

Adaptive exponential smoothing


Smoothing coefficient () is varied

Box-Jenkins method
Requires about 60 periods of past data

11-17

Time Series vs. Causal Models


Time series compares data being forecast over time, i.e. Time is the independent variable or x- axis or x-variable. Causal models compare data being forecast against some other data set which the forecaster may think is a cause of the forecasted data, e.g. population size causes newspaper sales.
11-18

Causal Forecasting Models


The general regression model:

a bx y
Other forms of causal model:
Econometric Input-output Simulation models

11-19

Example of Time Series Model


Yt = a + b(t)
t 1 2 3 4 5 6 7 Intercept (a) Slope (b) Dt 120 124 119 124 125 130 Ft 119.52 121.18 122.84 124.5 126.15 127.81 129.47

Dt = actual sales Ft = forecasted sales t = time period (e.g. year)

117.8667 1.657143

F7 = 117.87 + 1.66 (7) = 129.47 = sales forecast for next year


11-20

Example of Causal Model


Yt = a + b(t)
It 34.6 35.7 36.3 35.2 35.7 36.4 37.6 Intercept (a) Slope (b) Dt 120 124 119 124 125 130 Ft 121.15 123.79 125.22 122.59 123.79 125.46 128.34

Dt = actual sales in year t Ft = forecasted sales It = median family income (000s)

38.23094 2.396514

F7 = 38.23 + 2.397 (7) = 128.34 = sales forecast for next year (year 7)
11-21

Selecting a Forecasting Method


User and system sophistication
People reluctant to use what they dont understand

Time and resources available


When is forecast needed? What is value of forecast?

Use or decision characteristics, e.g. horizon Data availability and quality Data pattern Dont force the data to fit the model!
11-22

Forecast Horizons and Forecast Accuracy


The longer the forecast horizon, the less accurate the forecast Long lead times require long forecast horizons Lean, responsive companies have the goal of decreasing lead times so they are shorter than the forecast horizon

Collaborative Planning, Forecasting and Replenishment (CPFR)


Aim is to achieve more accurate forecasts Share information in the supply chain with customers and suppliers. Compare forecasts
If discrepancy, look for reason Agree on consensus forecast

Works best in BtoB with few customers

11-24

Summary
A Forecasting Framework Qualitative Forecasting Methods Time-Series Forecasting Moving Average Exponential Smoothing Forecast Errors Advanced Time-Series Forecasting Causal Forecasting Methods Selecting a Forecasting Method Collaborative Planning, Forecasting and Replenishment
11-25

End of Chapter Eleven

11-26

You might also like