05 Forecasting

8/2/2019 05 Forecasting

1/81

2008 Prentice-Hall, Inc.

Chapter 5

To accompanyQuantitative Analysis for Management, Tenth Edition,by

Render, Stair, and HannaPower Point slides created by Jeff Heyl

Forecasting

2009 Prentice-Hall, Inc.


2/81

2009 Prentice-Hall, Inc. 5 2

Introduction

Managers are always trying to reduceuncertainty and make better estimates of whatwill happen in the future

This is the main purpose of forecasting Some firms use subjective methods

Seat-of-the pants methods, intuition,experience

There are also several quantitative techniques Moving averages, exponential smoothing,

trend projections, least squares regressionanalysis


3/81


Introduction

Forecasting is a method for translating pastexperience into estimates of the future

Virtually used by most management decisionssuch as:

Working capital needs Size of workforce Inventory levels Scheduling of production runs


4/81


Introduction

Judgmental Forecasting is used when situations inwhich human judgment is the only realisticforecasting method

It is especially used when: There are a few data for building a quantitative

model

Historical data are no longer representative due

to drastic environmental changes Decision to be taken is critical If the forecaster views himself as an expert in

the area


5/81


Introduction

Judgmental Forecasting Evaluated:

Trends in the data caused by seasonal patterns

may be overlooked

Human judgment may be biased based on thefollowing types:

Gamblers fallacy Conservatism


6/81


Introduction

Eight steps to forecasting :

1. Determine the use of the forecastwhatobjective are we trying to obtain?

2. Select the items or quantities that are to be

forecasted3. Determine the time horizon of the forecast

4. Select the forecasting model or models

5. Gather the data needed to make the forecast

6. Validate the forecasting model7. Make the forecast

8. Implement the results


7/81 2009 Prentice-Hall, Inc. 5 7

Introduction

These steps are a systematic way of initiating,designing, and implementing a forecastingsystem

When used regularly over time, data is collected

routinely and calculations performedautomatically

There is seldom one superior forecastingsystem

Different organizations may use differenttechniques Whatever tool works best for a firm is the one

they should use



Regression Analysis

MultipleRegression

MovingAverage

ExponentialSmoothing

TrendProjections

Decomposition

DelphiMethods

Jury of ExecutiveOpinion

Sales ForceComposite

ConsumerMarket Survey

Time-Series MethodsQualitativeModels

CausalMethods

Forecasting Models

ForecastingTechniques

Figure 5.1



Time-Series Models

Time-series models attempt to predictthe future based on the past

Common time-series models are Moving average Exponential smoothing Trend projections Decomposition

Regression analysis is used in trendprojections and one type ofdecomposition model



Causal Models

Causal modelsCausal models use variables or factorsthat might influence the quantity beingforecasted

The objective is to build a model withthe best statistical relationship betweenthe variable being forecast and theindependent variables

Regression analysis is the mostcommon technique used in causalmodeling



Qualitative Models

Qualitative modelsQualitative models incorporate judgmentalor subjective factors

Useful when subjective factors are

thought to be important or when accuratequantitative data is difficult to obtain

Common qualitative techniques are Delphi method

Jury of executive opinion Sales force composite Consumer market surveys



Qualitative Models

Delphi MethodDelphi Method an iterative group process where(possibly geographically dispersed) respondentsrespondentsprovide input to decision makersdecision makers

Jury of Executive OpinionJury of Executive Opinion collects opinions of a

small group of high-level managers, possiblyusing statistical models for analysis

Sales Force CompositeSales Force Composite individual salespersonsestimate the sales in their region and the data is

compiled at a district or national level Consumer Market SurveyConsumer Market Survey input is solicited from

customers or potential customers regarding theirpurchasing plans



Quantitative forecasting models assume that thetime series follows some pattern called theforecast profiles

The 4 kinds of trends are:

Constant Level-assumes no trend at all in the data Linear Trend

- forecast a straight-line trend

Exponential Trend- forecast that the amount of growth will increasecontinuously

Damped Trend- the amount of trend declines in each period and diesout to form a horizontal line

Time Series Patterns



Time-series Patterns

The 3 kinds of seasonalities:1. Nonseasonal Pattern

- assumed to have a relatively constant mean

1. Additive Seasonal Pattern- assumes that the seasonal fluctuations are

of constant size

1. Multiplicative Seasonal Pattern

- assumes that the seasonal fluctuations areproportional to the data


15/81


Scatter Diagrams

0

50100

150

200

250

300

350

400

450

0 2 4 6 8 10 12

Time (Years)

AnnualSales

Radios

Televisions

CompactDiscs

Scatter diagrams are helpful when forecasting time-series databecause they depict the relationship between variables.


16/81


Scatter Diagrams

Wacker Distributors wants to forecast sales for threedifferent products

YEAR TELEVISION SETS RADIOS COMPACT DISC PLAYERS

1 250 300 110

2 250 310 1003 250 320 120

4 250 330 140

5 250 340 170

6 250 350 150

7 250 360 160

8 250 370 190

9 250 380 200

10 250 390 190

Table 5.1


17/81


Scatter Diagrams

Figure 5.2

330

250

200

150

100

50

| | | | | | | | | |

0 1 2 3 4 5 6 7 8 9 10

Time (Years)

AnnualSalesofT

elevisions

(a) Sales appear to be

constant over time

Sales = 250 A good estimate of

sales in year 11 is250 televisions


18/81


Scatter Diagrams

Sales appear to beincreasing at aconstant rate of 10

radios per yearSales = 290 + 10(Year)

A reasonableestimate of sales in

year 11 is 400televisions

420

400

380

360

340

320

300

280

| | | | | | | | | |

0 1 2 3 4 5 6 7 8 9 10

Time (Years)

AnnualSalesofR

adios

(b)

Figure 5.2


19/81


Scatter Diagrams

This trend line maynot be perfectlyaccurate because ofvariation from year toyear

Sales appear to beincreasing

A forecast wouldprobably be a larger

figure each year

200

180

160

140

120

100

| | | | | | | | | |

0 1 2 3 4 5 6 7 8 9 10

Time (Years)

AnnualSalesofCD

Players

(c)

Figure 5.2


20/81


21/81


Measures of Forecast Accuracy

Using a navenave forecasting modelYEAR ACTUAL

SALES OF CDPLAYERS

FORECAST SALES ABSOLUTE VALUE OFERRORS (DEVIATION), (ACTUAL

FORECAST)

1 110

2 100 110 |100 110| = 10

3 120 100 |120 110| = 20

4 140 120 |140 120| = 20

5 170 140 |170 140| = 30

6 150 170 |150 170| = 20

7 160 150 |160 150| = 10

8 190 160 |190 160| = 309 200 190 |200 190| = 10

10 190 200 |190 200| = 10

11 190

Sum of |errors| = 160

MAD = 160/9 = 17.8Table 5.2


22/81



Using a navenave forecasting modelYEAR ACTUAL

SALES OF CDPLAYERS

FORECAST SALES ABSOLUTE VALUE OFERRORS (DEVIATION), (ACTUAL

FORECAST)

1 110

2 100 110 |100 110| = 10

3 120 100 |120 110| = 20

4 140 120 |140 120| = 20

5 170 140 |170 140| = 30

6 150 170 |150 170| = 20

7 160 150 |160 150| = 10

8 190 160 |190 160| = 309 200 190 |200 190| = 10

10 190 200 |190 200| = 10

11 190

Sum of |errors| = 160

MAD = 160/9 = 17.8Table 5.2

8179

160errorforecast.MAD =

n


23/81



There are other popular measures of forecastaccuracy

The mean squared errormean squared error

n

=2error)(

MSE

The mean absolute percent errormean absolute percent error

%MAPE 100actual

error

n

= And biasbias is the average error and tells whether the

forecast tends to be too high or too low and by how

much. Thus, it can be negative or positive.


24/81



Year Actual CD Sales Forecast Sales |Actual -Forecast|

1 110

2 100 110 10

3 120 100 20

4 140 120 20

5 170 140 30

6 150 170 20

7 160 150 10

8 190 160 30

9 200 190 10

10 190 200 10

11 190

Sum of |errors| 160

MAD 17.8


25/81


Hospital Days Forecast ErrorExample

Ms. Smith forecastedtotal hospital inpatientdays last year. Now thatthe actual data areknown, she isreevaluating herforecasting model.

Compute the MAD,

MSE, and MAPE for herforecast.

Month Forecast Actual

JAN 250 243

FEB 320 315

MAR 275 286

APR 260 256MAY 250 241

JUN 275 298

JUL 300 292

AUG 325 333

SEP 320 326

OCT 350 378

NOV 365 382

DEC 380 396


26/81


Hospital Days Forecast ErrorExample

Forecast Actual |error| error 2

|error/actual|

JAN 250 243 7 49 0.03

FEB 320 315 5 25 0.02

MAR 275 286 11 121 0.04

APR 260 256 4 16 0.02

MAY 250 241 9 81 0.04

JUN 275 298 23 529 0.08

JUL 300 292 8 64 0.03

AUG 325 333 8 64 0.02

SEP 320 326 6 36 0.02

OCT 350 378 28 784 0.07 NOV 365 382 17 289 0.04

DEC 380 396 16 256 0.04

AVERAGEMAD=11.83

MSE=192.83

MAPE=.0381*100 =3.81


27/81


Time-Series Forecasting Models

A time series is a sequence of evenlyspaced events (weekly, monthly, quarterly,etc.)

Time-series forecasts predict the futurebased solely of the past values of thevariable

Other variables, no matter how potentially

valuable, are ignored


28/81


Decomposition of a Time-Series

A time series typically has four components

1.1. TrendTrend(TT) is the gradual upward ordownward movement of the data over time

2.2. SeasonalitySeasonality(SS

) is a pattern of demandfluctuations above or below trend line thatrepeats at regular intervals

3.3. CyclesCycles (CC) are patterns in annual data thatoccur every several years

4.4. Random variationsRandom variations (RR) are blips in thedata caused by chance and unusualsituations


29/81



Average Demandover 4 Years

TrendComponent

ActualDemand

Line

Time

De

mandforProduct

orService

| | | |

Year Year Year Year 1 2 3 4

Seasonal Peaks

Figure 5.3


30/81



There are two general forms of time-seriesmodels

The multiplicative model

Demand = Tx Sx Cx R

The additive model

Demand = T+ S+ C+ R

Models may be combinations of these two forms Forecasters often assume errors are normally

distributed with a mean of zero


31/81


Moving Averages

Moving averagesMoving averages can be used when demand isrelatively steady over time

The next forecast is the average of the most

recent n data values from the time series The most recent period of data is added and the

oldest is droppedThis methods tends to smooth out short-term

irregularities in the data series

n

nperiodspreviousindemandsofSumforecastaverageMoving =


32/81


Moving Averages

Mathematically

n

YYYF

nttt

t

111

+++= ...

where

= forecast for time period t+ 1

= actual value in time period t

n = number of periods to average

tY

1tF


33/81


Wallace Garden Supply Example

Wallace Garden Supply wants to forecastdemand for its Storage Shed

They have collected data for the past year

They are using a three-month movingaverage to forecast demand (n = 3)


34/81



Table 5.3

MONTH ACTUAL SHED SALES THREE-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

(12 + 13 + 16)/3 = 13.67

(13 + 16 + 19)/3 = 16.00

(16 + 19 + 23)/3 = 19.33

(19 + 23 + 26)/3 = 22.67

(23 + 26 + 30)/3 = 26.33

(26 + 30 + 28)/3 = 28.00

(30 + 28 + 18)/3 = 25.33

(28 + 18 + 16)/3 = 20.67

(18 + 16 + 14)/3 = 16.00

(10 + 12 + 13)/3 = 11.67


35/81


Weighted Moving Averages

Weighted moving averagesWeighted moving averages use weights to put moreemphasis on recent periods

Often used when a trend or other pattern is emerging

= )( ))(( Weights periodinvalueActualperiodinWeight1 iFt Mathematically

n

ntntt

twww

YwYwYwF +

+= ++...

...

21

11211

ere

wi= weight for the ith observation


36/81


Weighted Moving Averages

Both simple and weighted averages areeffective in smoothing out fluctuations in thedemand pattern in order to provide stableestimates

ProblemsIncreasing the size ofn smoothes outfluctuations better, but makes the method lesssensitive to real changes in the data

Moving averages can not pick up trends verywell they will always stay within past levels andnot predict a change to a higher or lower level


37/81



Wallace Garden Supply decides to try a weightedmoving average model to forecast demand for itsStorage Shed

They decide on the following weighting scheme

WEIGHTS APPLIED PERIOD

3 Last month

2 Two months ago

1 Three months ago

6

3 x Sales last month + 2 x Sales two months ago + 1 X Sales three months ago

Sum of the weights


38/81



Table 5.4

MONTH ACTUAL SHED SALES THREE-MONTH WEIGHTEDMOVING AVERAGE

January 10

February 12

March 13

April 16

May 19

June 23

July 26

August 30

September 28

October 18

[(3 X 13) + (2 X 12) + (10)]/6 = 12.17[(3 X 16) + (2 X 13) + (12)]/6 = 14.33

[(3 X 19) + (2 X 16) + (13)]/6 = 17.00

[(3 X 23) + (2 X 19) + (16)]/6 = 20.50

[(3 X 26) + (2 X 23) + (19)]/6 = 23.83

[(3 X 30) + (2 X 26) + (23)]/6 = 27.50

[(3 X 28) + (2 X 30) + (26)]/6 = 28.33

[(3 X 18) + (2 X 28) + (30)]/6 = 23.33

[(3 X 16) + (2 X 18) + (28)]/6 = 18.67

[(3 X 14) + (2 X 16) + (18)]/6 = 15.33


39/81



Program 5.1A


40/81



Program 5.1B


41/81


Exponential Smoothing

Exponential smoothingExponential smoothingis easy to use andrequires little record keeping of data

It is a type of moving average

ecast = Last periods forecast+ (Last periods actual demand Last periods forecast)

Where is a weight (orsmoothing constantsmoothing constant) witha value between 0 and 1 inclusive

A largergives more importance to recent datawhile a smaller value gives more importance to

past data


42/81


43/81


Exponential Smoothing Example

In January, Februarys demand for a certaincar model was predicted to be 142

Actual February demand was 153 autos Using a smoothing constant of = 0.20, what

is the forecast for March?

New forecast (for March demand) = 142 + 0.2(153 142)

= 144.2 or 144 autos

If actual demand in March was 136 autos, theApril forecast would be

New forecast (for April demand) = 144.2 + 0.2(136 144.2)

= 142.6 or 143 autos


44/81


Selecting the Smoothing Constant

Selecting the appropriate value foris key toobtaining a good forecast

The objective is always to generate an

accurate forecast The general approach is to develop trial

forecasts with different values ofand selectthe that results in the lowest MAD


45/81


Port of Baltimore Example

QUARTER ACTUALTONNAGE

UNLOADED

FORECASTUSING =0.10

FORECASTUSING =0.50

1 180 175 175

2 168 175.5 = 175.00 + 0.10(180 175) 177.5

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 ? 178.60 = 178.22 + 0.10(182 178.22) 184.15

Table 5.5

Exponential smoothing forecast for two values of


46/81


Selecting the Best Value ofQUARTER ACTUAL

TONNAGEUNLOADED

FORECASTWITH = 0.10

ABSOLUTEDEVIATIONSFOR = 0.10

FORECASTWITH = 0.50

ABSOLUTEDEVIATIONSFOR = 0.50

1 180 175 5.. 175 5.

2 168 175.57.5..

177.59.5..

3 159 174.7515.75

172.7513.75

4 175 173.181.82

165.889.12

5 190 173.3616.64

170.4419.56

6 205 175.0229.98

180.2224.78

7 180 178.021.98

192.6112.61

8 182 178.223.78

186.304.3..

Sum of absolute deviations 82.45 98.63

MAD = |deviations| = 10.31 MAD = 12.33

Table 5.6Best choiceBest choice


47/81



Program 5.2A


48/81



Program 5.2B


49/81


PM Computer: Moving AverageExample

PM Computer assembles customized personalcomputers from generic parts

The owners purchase generic computer parts involume at a discount from a variety of sourceswhenever they see a good deal.

It is important that they develop a good forecast ofdemand for their computers so they can purchasecomponent parts efficiently.


50/81


PM Computers: Data

Period Month Actual Demand1 Jan 37

2 Feb 40

3 Mar 41

4 Apr 37

5 May 456 June 50

7 July 43

8 Aug 47

9 Sept 56

Compute a 2-month moving average Compute a 3-month weighted average using weights of

4,2,1 for the past three months of data Compute an exponential smoothing forecast using = 0.7,

previous forecast of 40

Using MAD, what forecast is most accurate?


51/81


PM Computers: Moving AverageSolution

2 monthMA Abs. Dev 3monthWMA Abs. Dev Exp.Sm. Abs. Dev

37.00

37.00 3.00

38.50 2.50 39.10 1.90

40.50 3.50 40.14 3.14 40.43 3.43

39.00 6.00 38.57 6.43 38.03 6.97

41.00 9.00 42.14 7.86 42.91 7.09

47.50 4.50 46.71 3.71 47.87 4.87

46.50 0.50 45.29 1.71 44.46 2.54

45.00 11.00 46.29 9.71 46.24 9.76

51.50 51.57 53.07

5.29 5.43 4.95MADExponential smoothing resulted in the lowest MAD.


52/81


Exponential Smoothing withTrend Adjustment

Like all averaging techniques, exponentialsmoothing does not respond to trends

A more complex model can be used thatadjusts for trends

The basic approach is to develop anexponential smoothing forecast then adjust itfor the trend

New forecast (Ft)+ Trend correction (T

t)

S


53/81


Exponential Smoothing withTrend Adjustment

The equation for the trend correction uses anew smoothing constant

Ttis computed by

)()1( 11 tttt FFTT += ++

where

Tt+1 = smoothed trend for period t+ 1

Tt= smoothed trend for preceding period

= trend smooth constant that we select

Ft+1 = simple exponential smoothed forecast

for period t+ 1

Ft= forecast for pervious period


54/81


Selecting a Smoothing Constant

As with exponential smoothing, a high value ofmakes the forecast more responsive to changes intrend

A low value ofgives less weight to the recent trend

and tends to smooth out the trend Values are generally selected using a trial-and-error

approach based on the value of the MAD for differentvalues of

Simple exponential smoothing is often referred to asfirst-order smoothingfirst-order smoothing

Trend-adjusted smoothing is called second-ordersecond-order,double smoothingdouble smoothing, orHolts methodHolts method


55/81


Trend Projection

Trend projection fits a trend line to a seriesof historical data points

The line is projected into the future for

medium- to long-range forecasts Several trend equations can be developed

based on exponential or quadratic models

The simplest is a linear model developed

using regression analysis


56/81


57/81


Trend Projection

The mathematical form is

XbbY 10 +

where

= predicted value

b0 = intercept

b1 = slope of the line

X = time period (i.e., X= 1, 2, 3, , n)

Y


58/81


Trend Projection

ValueofDependentVariable

Time

*

*

*

*

*

*

*Dist2

Dist4

Dist6

Dist1

Dist3

Dist5

Dist7

Figure 5.4

Mid t M f t i


59/81


Midwestern ManufacturingCompany Example

Midwestern Manufacturing Company has experiencedthe following demand for its electrical generators overthe period of 2001 2007

YEAR ELECTRICAL GENERATORS SOLD

2001 74

2002 79

2003 80

2004 90

2005 1052006 142

2007 122

Table 5.7

Mid t M f t i


60/81



Program 5.3A

Notice codeinstead of

actual years


61/81

Mid t M f t i


62/81



The forecast equation is

XY 54107156 .. +

To project demand for 2008, we use the coding

system to define X= 8

(sales in 2008) = 56.71 + 10.54(8)

= 141.03, or 141 generators

Likewise forX= 9

(sales in 2009) = 56.71 + 10.54(9)

= 151.57, or 152 generators

Mid t M f t i


63/81



GeneratorDem

and

Year

160

150

140

130

120 110

100

90

80

70 60

50

| | | | | | | | |

2001 2002 2003 2004 2005 2006 2007 2008 2009

Actual Demand Line

Trend LineXY 54107156 .. +

Figure 5.5

Mid t M f t i


64/81



Program 5.4A

Mid t M f t i


65/81



Program 5.4B


66/81


Seasonal Variations

Recurring variations over time mayindicate the need for seasonaladjustments in the trend line

A seasonal index indicates how aparticular season compares with anaverage season

When no trend is present, the seasonalindex can be found by dividing theaverage value for a particular season bythe average of all the data


67/81


Seasonal Variations

Eichler Supplies sells telephoneanswering machines

Data has been collected for the past two

years sales of one particular model They want to create a forecast that

includes seasonality


68/81


Seasonal Variations

MONTH SALES DEMAND AVERAGE TWO-YEAR DEMAND

MONTHLYDEMAND

AVERAGESEASONAL

INDEXYEAR 1 YEAR 2

January 80 10090

94 0.957

February 85 7580

94 0.851

March 80 9085

94 0.904

April 110 90100

94 1.064

May 115 131123

94 1.309

June 120 110115

94 1.223

July 100 110105

94 1.117

August 110 90100

94 1.064

September 85 95

90

94 0.957Seasonal index =

Average two-year demand

Average monthly demandAverage monthly demand = = 94

1,128

12 months

Table 5.8


69/81


Seasonal Variations

The calculations for the seasonal indices are

Jan. July96957012

2001=.

,1121171

12

2001 =.,

Feb. Aug.85851012

2001

=.,

106064112

2001=.

,

Mar. Sept.90904012

2001=.

,969570

12

2001=.

,

Apr. Oct.106064112

2001=.

,858510

12

2001=.

,

May Nov.131309112

2001 =., 85851012

2001=.

,

June Dec.122223112

2001 =.,

85851012

2001 =.,

Regression with Trend and


70/81


Regression with Trend andSeasonal Components

Multiple regressionMultiple regression can be used to forecast bothtrend and seasonal components in a time series

One independent variable is time Dummy independent variables are used to represent

the seasons

The model is an additive decomposition model

where

X1 = time periodX2 = 1 if quarter 2, 0 otherwise

X3 = 1 if quarter 3, 0 otherwise

X4 = 1 if quarter 4, 0 otherwise

44332211 XbXbXbXbaY +



71/81



Program 5.6A



72/81



Program 5.6B (partial)



73/81



The resulting regression equation is

4321 130738715321104 XXXXY ..... +

Using the model to forecast sales for the first two

quarters of next year

These are different from the results obtained using themultiplicative decomposition method

Use MAD and MSE to determine the best model

13401300738071513321104 =)(.)(.)(.)(..Y15201300738171514321104 =)(.)(.)(.)(..Y



74/81



American Airlines original spare parts inventorysystem used only time-series methods to forecastthe demand for spare parts

This method was slow to responds to even moderatechanges in aircraft utilization let alone major fleet

expansions They developed a PC-based system named RAPS

which uses linear regression to establish arelationship between monthly part removals andvarious functions of monthly flying hours

The computation now takes only one hour instead ofthe days the old system needed

Using RAPS provided a one time savings of $7 millionand a recurring annual savings of nearly $1 million


75/81


Monitoring and Controlling Forecasts

Tracking signalsTracking signalscan be used to monitor theperformance of a forecast

Tacking signals are computed using thefollowing equation

MAD

RSFE=signalTracking

n

= errorforecastMADwhere


76/81



AcceptableRange

Signal Tripped

Upper Control Limit

Lower Control Limit

0 MADs

+

Time

Figure 5.7

Tracking Signal


77/81



Positive tracking signals indicate demand is greaterthan forecast

Negative tracking signals indicate demand is less thanforecast

Some variation is expected, but a good forecast willhave about as much positive error as negative error

Problems are indicated when the signal trips either theupper or lower predetermined limits

This indicates there has been an unacceptable amountof variation

Limits should be reasonable and may vary from item toitem



78/81



How do you decide on the upper and lower limits? Too small a value will trip the signal too often and

too large will cause a bad forecast

Plossl & Wight use maximums of 4 MADs for

high volume stock items and 8 MADs for lowervolume items One MAD is equivalent to approximately 0.8

standard deviation so that 4 MADs =3.2 s.d.

For a forecast to be in control, 89% of the errorsare expected to fall within 2 MADs, 98% with 3MADs or 99.9% within 4 MADs whenever theerrors are approximately normally distributed

Ki b ll B k E l


79/81


Kimballs Bakery Example

Tracking signal for quarterly sales of croissantsTIME

PERIODFORECASTDEMAND

ACTUALDEMAND

ERROR RSFE |FORECAST || ERROR |

CUMULATIVEERROR

MAD TRACKINGSIGNAL

1 100 90 10 10 10 10 10.0 1

2 100 95 5 15 5 15 7.5 2

3 100 115 +15 0 15 30 10.0 0

4 110 100 10 10 10 40 10.0 1

5 110 125 +15 +5 15 55 11.0 +0.5

6 110 140 +30 +35 30 85 14.2 +2.5

2146

85errorforecast .MAD =n

sMAD..MAD

RSFE52

214

35signalTracking =


80/81


Forecasting at Disney

The Disney chairman receives a dailyThe Disney chairman receives a dailyreport from his main theme parks thatreport from his main theme parks thatcontains only two numbers thecontains only two numbers the forecastforecastof yesterdays attendance at the parks andof yesterdays attendance at the parks andthethe actualactualattendanceattendance

An error close to zero (using MAPE as themeasure) is expected

The annual forecast of total volume

conducted in 1999 for the year 2000resulted in a MAPE of 0


81/81

Using The Computer to Forecast

Spreadsheets can be used by small andmedium-sized forecasting problems

More advanced programs (SAS, SPSS,Minitab) handle time-series and causal

models May automatically select best model

parameters Dedicated forecasting packages may be

fully automatic May be integrated with inventory planning

and control

Documents

05 Forecasting