You are on page 1of 110

Operations

Management
Chapter 4 -
Forecasting
PowerPoint presentation to accompany
Heizer/Render
Principles of Operations Management, 6e
Operations Management, 8e

© 2006
© 2006 Prentice
Prentice Hall, Inc. Hall, Inc. 4–1

Outline
 Global Company Profile:
Tupperware Corporation
 What Is Forecasting?
 Forecasting Time Horizons
 The Influence of Product Life Cycle
 Types Of Forecasts

© 2006 Prentice Hall, Inc. 4–2

Outline – Continued
 The Strategic Importance Of
Forecasting
 Human Resources
 Capacity
 Supply-Chain Management
 Seven Steps In The Forecasting
System

© 2006 Prentice Hall, Inc. 4–3

Outline – Continued
 Forecasting Approaches
 Overview of Qualitative Methods
 Overview of Quantitative Methods

© 2006 Prentice Hall, Inc. 4–4

Outline – Continued
 Time-series Forecasting
 Decomposition of a Time Series
 Naïve Approach
 Moving Averages
 Exponential Smoothing
 Exponential Smoothing with Trend
Adjustment
 Trend Projections
 Seasonal Variations in Data
 Cyclical Variations in Data
© 2006 Prentice Hall, Inc. 4–5

Outline – Continued
 Associative Forecasting Methods:
Regression And Correlation
Analysis
 Using Regression Analysis to
Forecast
 Standard Error of the Estimate
 Correlation Coefficients for
Regression Lines
 Multiple-Regression Analysis

© 2006 Prentice Hall, Inc. 4–6

Outline – Continued  Monitoring And Controlling Forecasts  Adaptive Smoothing  Focus Forecasting  Forecasting In The Service Sector © 2006 Prentice Hall. Inc. 4–7 .

you should be able to : Identify or Define:  Forecasting  Types of forecasts  Time horizons  Approaches to forecasts © 2006 Prentice Hall. 4–8 . Learning Objectives When you complete this chapter. Inc.

4–9 . you should be able to : Describe or Explain:  Moving averages  Exponential smoothing  Trend projections  Regression and correlation analysis  Measures of forecast accuracy © 2006 Prentice Hall. Learning Objectives When you complete this chapter. Inc.

4 – 10 . and 12-month sales projections  These projections are aggregated by region. Inc. quarterly. at Tupperware’s World Headquarters  Tupperware uses all techniques discussed in text © 2006 Prentice Hall. Forecasting at Tupperware  Each of 50 profit centers around the world is responsible for computerized monthly. then globally.

4 – 11 . Tupperware’s Process © 2006 Prentice Hall. Inc.

4 – 12 . Inc. Three Key Factors for Tupperware  The number of registered “consultants” or sales representatives  The percentage of currently “active” dealers (this number changes each week and month)  Sales per active dealer. on a weekly basis © 2006 Prentice Hall.

finance. Inc. marketing. final forecasts are the consensus of all participating managers  The final step is Tupperware’s version of the “jury of executive opinion” © 2006 Prentice Hall. Forecast by Consensus  Although inputs come from sales. and production. 4 – 13 .

What is Forecasting?  Process of predicting a future event  Underlying basis of ?? all business decisions  Production  Inventory  Personnel  Facilities © 2006 Prentice Hall. 4 – 14 . Inc.

Forecasting Time Horizons  Short-range forecast  Up to 1 year. budgeting  Long-range forecast  3+ years  New product planning. Inc. generally less than 3 months  Purchasing. job scheduling. production levels  Medium-range forecast  3 months to 3 years  Sales and production planning. research and development © 2006 Prentice Hall. job assignments. 4 – 15 . workforce levels. facility location.

plants and processes  Short-term forecasting usually employs different methodologies than longer-term forecasting  Short-term forecasts tend to be more accurate than longer-term forecasts © 2006 Prentice Hall. 4 – 16 . Inc. Distinguishing Differences  Medium/long range forecasts deal with more comprehensive issues and support management decisions regarding planning and products.

4 – 17 . forecasts are useful in projecting  Staffing levels  Inventory levels  Factory capacity © 2006 Prentice Hall. Influence of Product Life Cycle Introduction – Growth – Maturity – Decline  Introduction and growth require longer forecasts than maturity and decline  As product passes through life cycle. Inc.

or quality R&D engineering is Strengthen niche Competitive costs critical become critical Defend market position CD-ROM Fax machines Internet Drive-through restaurants Color printers Sales 3 1/2” Floppy Flat-screen disks monitors DVD Figure 2. 4 – 18 . Inc.5 © 2006 Prentice Hall. Product Life Cycle Introduction Growth Maturity Decline Best period to Practical to change Poor time to Cost control Company Strategy/Issues increase market price or quality change image. critical share image price.

Inc.5 © 2006 Prentice Hall. Product Life Cycle Introduction Growth Maturity Decline Product design Forecasting Standardization Little product and critical differentiation Less rapid development Product and product changes Cost OM Strategy/Issues critical process – more minor minimization Frequent reliability changes Overcapacity product and Competitive Optimum in the process design product capacity industry changes improvements Increasing Prune line to Short production and options stability of eliminate runs Increase capacity process items not High production returning Shift toward Long production costs good margin product focus runs Limited models Reduce Enhance Product capacity Attention to distribution improvement and quality cost cutting Figure 2. 4 – 19 .

 Technological forecasts  Predict rate of technological progress  Impacts development of new products  Demand forecasts  Predict sales of existing product © 2006 Prentice Hall. housing starts. etc. Inc. 4 – 20 . Types of Forecasts  Economic forecasts  Address business cycle – inflation rate. money supply.

4 – 21 . Inc. loss of market share  Supply-Chain Management – Good supplier relations and price advance © 2006 Prentice Hall. training. laying off workers  Capacity – Capacity shortages can result in undependable delivery. loss of customers. Strategic Importance of Forecasting  Human Resources – Hiring.

Inc. Seven Steps in Forecasting  Determine the use of the forecast  Select the items to be forecasted  Determine the time horizon of the forecast  Select the forecasting model(s)  Gather the data  Make the forecast  Validate and implement results © 2006 Prentice Hall. 4 – 22 .

Inc. The Realities!  Forecasts are seldom perfect  Most techniques assume an underlying stability in the system  Product family and aggregated forecasts are more accurate than individual product forecasts © 2006 Prentice Hall. 4 – 23 .

. Inc. 4 – 24 . Forecasting Approaches Qualitative Methods  Used when situation is vague and little data exist  New products  New technology  Involves intuition. experience  e.g. forecasting sales on Internet © 2006 Prentice Hall.

Forecasting Approaches Quantitative Methods  Used when situation is ‘stable’ and historical data exist  Existing products  Current technology  Involves mathematical techniques  e. forecasting sales of color televisions © 2006 Prentice Hall.g.. Inc. 4 – 25 .

4 – 26 . queried iteratively © 2006 Prentice Hall. Overview of Qualitative Methods  Jury of executive opinion  Pool opinions of high-level executives. Inc. sometimes augment by statistical models  Delphi method  Panel of experts.

Inc. 4 – 27 . Overview of Qualitative Methods  Sales force composite  Estimates from individual salespersons are reviewed for reasonableness. then aggregated  Consumer Market Survey  Ask the customer © 2006 Prentice Hall.

4 – 28 . Jury of Executive Opinion  Involves small group of high-level managers  Group estimates demand by working together  Combines managerial experience with statistical models  Relatively quick  ‘Group-think’ disadvantage © 2006 Prentice Hall. Inc.

4 – 29 . Inc. Sales Force Composite  Each salesperson projects his or her sales  Combined at district and national levels  Sales reps know customers’ wants  Tends to be overly optimistic © 2006 Prentice Hall.

4 – 30 . responses and continues until make decisions) consensus is reached Staff (Administering  3 types of survey) participants  Decision makers  Staff Respondents (People who can  Respondents make valuable judgments) © 2006 Prentice Hall. Inc. Delphi Method  Iterative group Decision Makers (Evaluate process.

and what they actually do are often different  Sometimes difficult to answer © 2006 Prentice Hall. Consumer Market Survey  Ask customers about purchasing plans  What consumers say. Inc. 4 – 31 .

Overview of Quantitative Approaches 1. Naive approach 2. Inc. Trend projection Associative 5. Linear regression Model © 2006 Prentice Hall. 4 – 32 . Exponential Models smoothing 4. Moving averages Time-Series 3.

4 – 33 . Time Series Forecasting  Set of evenly spaced numerical data  Obtained by observing response variable at regular time periods  Forecast based only on past values  Assumes that factors influencing past and present will continue influence in future © 2006 Prentice Hall. Inc.

4 – 34 . Inc. Time Series Components Trend Cyclical Seasonal Random © 2006 Prentice Hall.

Components of Demand Trend component Demand for product or service Seasonal peaks Actual demand Average demand over Random four years variation | | | | 1 2 3 4 Year Figure 4.1 © 2006 Prentice Hall. 4 – 35 . Inc.

technology.  Typically several years duration © 2006 Prentice Hall. Inc. etc. 4 – 36 . Trend Component  Persistent. overall upward or downward pattern  Changes due to population. culture. age.

5 Month Day 28-31 Year Quarter 4 Year Month 12 Year Week 52 © 2006 Prentice Hall. etc. Seasonal Component  Regular pattern of up and down fluctuations  Due to weather. Inc. customs.  Occurs within a single year Number of Period Length Seasons Week Day 7 Month Week 4-4. 4 – 37 .

political. and economic factors  Multiple years duration  Often causal or associative relationships 0 5 10 15 20 © 2006 Prentice Hall. 4 – 38 . Cyclical Component  Repeating up and down movements  Affected by business cycle. Inc.

unsystematic. Inc. 4 – 39 . ‘residual’ fluctuations  Due to random variation or unforeseen events  Short duration and nonrepeating M T W T F © 2006 Prentice Hall. Random Component  Erratic.

g. then June sales will be 48  Sometimes cost effective and efficient © 2006 Prentice Hall.. 4 – 40 . Inc. Naive Approach  Assumes demand in next period is the same as demand in most recent period  e. If May sales were 48.

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 ∑ demand in previous n periods Moving average = n © 2006 Prentice Hall. Inc. 4 – 41 .

Moving Average Example Actual 3-Month Month Shed Sales Moving Average January 10 February 12 March 13 April 16 (10 + 12 + 13)/3 = 11 2/3 May 19 (12 + 13 + 16)/3 = 13 2/3 June 23 (13 + 16 + 19)/3 = 16 July 26 (16 + 19 + 23)/3 = 19 1/3 © 2006 Prentice Hall. 4 – 42 . Inc.

4 – 43 . Graph of Moving Average Moving 30 – Average 28 – Forecast 26 – Actual 24 – Sales Shed Sales 22 – 20 – 18 – 16 – 14 – 12 – 10 – | | | | | | | | | | | | J F M A M J J A S O N D © 2006 Prentice Hall. Inc.

4 – 44 . Weighted Moving Average  Used when trend is present  Older data usually less important  Weights based on experience and intuition ∑ (weight for period n) Weighted x (demand in period n) = moving average ∑ weights © 2006 Prentice Hall. Inc.

Inc. Weights Applied Period Weighted Moving 3 Average Last month 2 Two months ago 1 Three months ago 6 Sum of weights Actual 3-Month Weighted Month Shed Sales Moving Average January 10 February 12 March 13 April 16 [(3 x 13) + (2 x 12) + (10)]/6 = 121/6 May 19 [(3 x 16) + (2 x 13) + (12)]/6 = 141/3 June 23 [(3 x 19) + (2 x 16) + (13)]/6 = 17 July 26 [(3 x 23) + (2 x 19) + (16)]/6 = 201/2 © 2006 Prentice Hall. 4 – 45 .

Inc. 4 – 46 . Potential Problems With Moving Average  Increasing n smooths the forecast but makes it less sensitive to changes  Do not forecast trends well  Require extensive historical data © 2006 Prentice Hall.

2 © 2006 Prentice Hall. Moving Average And Weighted Moving Average 30 – Weighted moving average 25 – Sales demand 20 – Actual 15 – sales 10 – Moving average 5 – | | | | | | | | | | | | J F M A M J J A S O N D Figure 4. Inc. 4 – 47 .

4 – 48 . Exponential Smoothing  Form of weighted moving average  Weights decline exponentially  Most recent data weighted most  Requires smoothing constant ( )  Ranges from 0 to 1  Subjectively chosen  Involves little record keeping of past data © 2006 Prentice Hall. Inc.

Inc. Exponential Smoothing t = last period’s forecast +  (last period’s actual demand – last period’s forecast) Ft = Ft – 1 +  (At – 1 .Ft – 1) where Ft = new forecast Ft – 1 = previous forecast  = smoothing (or weighting) constant (0    1) © 2006 Prentice Hall. 4 – 49 .

4 – 50 . Inc. Exponential Smoothing Example Predicted demand = 142 Ford Mustangs Actual demand = 153 Smoothing constant  = .20 © 2006 Prentice Hall.

4 – 51 . Inc. Exponential Smoothing Example Predicted demand = 142 Ford Mustangs Actual demand = 153 Smoothing constant  = .20 New forecast = 142 + .2(153 – 142) © 2006 Prentice Hall.

20 New forecast = 142 + .2(153 – 142) = 142 + 2. Exponential Smoothing Example Predicted demand = 142 Ford Mustangs Actual demand = 153 Smoothing constant  = .2 ≈ 144 cars © 2006 Prentice Hall.2 = 144. Inc. 4 – 52 .

 )4  = .031 © 2006 Prentice Hall.063 . 4 – 53 .5 .073 .125 . ) 3  (1 .1 .5 .1 .066  = . Inc. ) 2  (1 .081 .09 . )  (1 .25 . Effect of Smoothing Constants Weight Assigned to Most 2nd Most 3rd Most 4th Most 5th Most Recent Recent Recent Recent Recent Smoothing Period Period Period Period Period Constant ( )  (1 .

Inc. Impact of Different  225 – 200 – Actual  = . 4 – 54 .1 | | | | | | | | | 1 2 3 4 5 6 7 8 9 Quarter © 2006 Prentice Hall.5 demand Demand 175 – 150 –  = .

Choosing  The objective is to obtain the most accurate forecast no matter the technique We generally do this by selecting the model that gives us the lowest forecast error Forecast error = Actual demand . 4 – 55 .Ft © 2006 Prentice Hall. Inc.Forecast value = At .

Inc. 4 – 56 .forecast| MAD = n Mean Squared Error (MSE) ∑ (forecast errors)2 MSE = n © 2006 Prentice Hall. Common Measures of Error Mean Absolute Deviation (MAD) ∑ |actual .

forecasti|/actuali i=1 MAPE = n © 2006 Prentice Hall. Inc. Common Measures of Error Mean Absolute Percent Error (MAPE) n 100 ∑ |actuali . 4 – 57 .

10  = . 4 – 58 . Inc.10  = .50  = .50 1 180 175 5 175 5 2 168 176 8 178 10 3 159 175 16 173 14 4 175 173 2 166 9 5 190 173 17 170 20 6 205 175 30 180 25 7 180 178 2 193 13 8 182 178 4 186 4 84 100 © 2006 Prentice Hall. Comparison of Forecast Error Rounded Absolute Rounded Absolute Actual Forecast Deviation Forecast Deviation Tonnage with for with for Quarter Unloaded  = .

50 173 2 166 9 5 190 173 17 170 20 6 205 = 100/8 175 = 12. 4 – 59 . Comparison of Forecast Error ∑ |deviations| Rounded Absolute Rounded Absolute MADActual = n Forecast Deviation Forecast Deviation Tonage with for with for Quarter Unloaded  = .10 175 5 175 5 2 168 = 84/8 = 10.10  = .5030 180 25 7 180 178 2 193 13 8 182 178 4 186 4 84 100 © 2006 Prentice Hall.50 1 For  = 180 .10  = . Inc.50  = .50 176 8 178 10 3 159 175 16 173 14 4 For 175 = .

Inc.50 © 2006 Prentice Hall.10  = .612/8 205 = 175 201.50 173 2 166 9 5 190 173 17 170 20 6 = 1.50 1 For  = 180 . 4 – 60 .50  = .5030 180 25 7 180 178 2 193 13 8 182 178 4 186 4 84 100 MAD 10.10  = .758 176 178 10 3 159 175 16 173 14 4 For 175 = . Comparison of Forecast Error ∑ (forecast errors) 2 MSE = Actual Rounded n Forecast Absolute Deviation Rounded Forecast Absolute Deviation Tonage with for with for Quarter Unloaded  = .50 12.558/8 168 = 194.10 175 5 175 5 2 = 1.

8/8 175 = 6. Comparison of Forecast n Error|/actual 100 ∑ |deviation i i i =Rounded 1 Absolute Rounded Absolute MAPE = Actual Forecast n Deviation Forecast Deviation Tonage with for with for Quarter Unloaded  = . 4 – 61 .10  = .10  = .75 201.50 © 2006 Prentice Hall. Inc.50 173 2 166 9 5 190 173 17 170 20 6 205 = 54.10 175 For 180 5 175 5 2 168 = 45.50  = .50 12.50 MSE 194.70% 8 178 10 3 159 175 16 173 14 4 For = 175 .50 1  = .62/8 176 = 5.85% 30 180 25 7 180 178 2 193 13 8 182 178 4 186 4 84 100 MAD 10.

Inc. 4 – 62 .75 201.70% 6.10  = . Comparison of Forecast Error Rounded Absolute Rounded Absolute Actual Forecast Deviation Forecast Deviation Tonnage with for with for Quarter Unloaded  = .50  = .50 12.85% © 2006 Prentice Hall.50 MAPE 5.50 1 180 175 5 175 5 2 168 176 8 178 10 3 159 175 16 173 14 4 175 173 2 166 9 5 190 173 17 170 20 6 205 175 30 180 25 7 180 178 2 193 13 8 182 178 4 186 4 84 100 MAD 10.10  = .50 MSE 194.

Exponential Smoothing with Trend Adjustment When a trend is present. Inc. exponential smoothing must be modified Forecast exponentially exponentially including (FITt) = smoothed (Ft) + (Tt) smoothed trend forecast trend © 2006 Prentice Hall. 4 – 63 .

Exponential Smoothing with Trend Adjustment Ft =  (At . Inc.1 Step 1: Compute Ft Step 2: Compute Tt Step 3: Calculate the forecast FITt = Ft + Tt © 2006 Prentice Hall.1 + Tt .1) + (1 .1) + (1 . )(Ft . )Tt .1) Tt =  (Ft .Ft . 4 – 64 .

4 – 65 . FITt 1 12 11 2 13.00 2 17 3 20 4 19 5 24 6 21 7 31 8 28 9 36 10 Table 4. Inc.1 © 2006 Prentice Hall. Tt Trend. Exponential Smoothing with Trend Adjustment Example Forecast Actual Smoothed Smoothed Including Month(t) Demand (At) Forecast. Ft Trend.

00 2 17 3 20 4 19 5 24 Step 1: Forecast for Month 2 6 21 F2 = A1 + (1 .)(F1 + T1) 7 31 8 28 F2 = (.1 © 2006 Prentice Hall. Tt Trend.2)(11 + 2) 9 36 10 = 2..4 = 12. Inc.4 + 10. Exponential Smoothing with Trend Adjustment Example Forecast Actual Smoothed Smoothed Including Month(t) Demand (At) Forecast. FITt 1 12 11 2 13.8 units Table 4. Ft Trend. 4 – 66 .2)(12) + (1 .

1 © 2006 Prentice Hall.92 units Table 4.4)(2) 9 36 10 = . Exponential Smoothing with Trend Adjustment Example Forecast Actual Smoothed Smoothed Including Month(t) Demand (At) Forecast. Tt Trend.. Ft Trend.00 2 17 12.4)(12.8 .)T1 7 31 8 28 T2 = (.F1) + (1 . 4 – 67 .11) + (1 .2 = 1. FITt 1 12 11 2 13.80 3 20 4 19 5 24 Step 2: Trend for Month 2 6 21 T2 = (F2 .72 + 1. Inc.

92 3 20 4 19 5 24 Step 3: Calculate FIT for Month 2 6 21 FIT2 = F2 + T1 7 31 8 28 FIT2 = 12. Ft Trend. Exponential Smoothing with Trend Adjustment Example Forecast Actual Smoothed Smoothed Including Month(t) Demand (At) Forecast.80 1. Inc. Tt Trend.92 9 36 10 = 14. FITt 1 12 11 2 13.72 units Table 4. 4 – 68 .1 © 2006 Prentice Hall.00 2 17 12.8 + 1.

16 Table 4.80 1.32 31. 4 – 69 .23 22.72 3 20 15.48 2.28 4 19 17.92 14.60 10 32. Ft Trend. Exponential Smoothing with Trend Adjustment Example Forecast Actual Smoothed Smoothed Including Month(t) Demand (At) Forecast.32 20.14 2.91 2.10 17.82 2.68 35.45 29.00 2 17 12.07 26.1 © 2006 Prentice Hall.59 9 36 29.11 2.18 8 28 27. FITt 1 12 11 2 13.51 2.89 7 31 24.18 2.38 24.14 6 21 22.14 5 24 19.28 2. Tt Trend. Inc.

3 Time (month) © 2006 Prentice Hall. 4 – 70 . Exponential Smoothing with Trend Adjustment Example 35 – 30 – Actual demand (At) Product demand 25 – 20 – 15 – 10 – Forecast including trend (FITt) 5 – 0 – | | | | | | | | | 1 2 3 4 5 6 7 8 9 Figure 4. Inc.

Trend Projections Fitting a trend line to historical data points to project into the medium-to-long-range Linear trends can be found using the least squares technique y^ = a + bx ^ where y = computed value of the variable to be predicted (dependent variable) a = y-axis intercept b = slope of the regression line © 2006 Prentice Hall. Inc. x = the independent variable 4 – 71 .

y^ = a + bx Time period Figure 4. Values of Dependent Variable Least Squares Method Actual observation Deviation7 (y value) Deviation5 Deviation6 Deviation3 Deviation4 Deviation1 Deviation2 Trend line. Inc.4 © 2006 Prentice Hall. 4 – 72 .

Inc.4 © 2006 Prentice Hall. y^ = a + bx Time period Figure 4. Values of Dependent Variable Least Squares Method Actual observation Deviation7 (y value) Deviation5 Deviation6 Deviation3 Least squares method minimizes the sum of the Deviation squared errors (deviations) 4 Deviation1 Deviation2 Trend line. 4 – 73 .

4 – 74 .nx2 a = y .bx © 2006 Prentice Hall.nxy b=  x2 . Inc. Least Squares Method Equations to calculate the regression variables y^ = a + bx  xy .

(7)(4)(98.(7)(42) = 10.063 .86 . Least Squares Example Time Electrical Power Year Period (x) Demand x2 xy 1999 1 74 1 74 2000 2 79 4 158 2001 3 80 9 240 2002 4 90 16 360 2003 5 105 25 525 2004 6 142 36 852 2005 7 122 49 854 ∑x = 28 ∑y = 692 ∑x2 = 140 ∑xy = 3.86) b= = 140 .nx2 a = y .10.54 ∑x2 . Inc.bx = 98.54(4) = 56. 4 – 75 .70 © 2006 Prentice Hall.86 ∑xy .063 x=4 y = 98.nxy 3.

10.nx2 = 140 .nxy 3. 4 – 76 .063 .54 a = y . Inc.70 © 2006 Prentice Hall.86 . Least Squares Example Time Electrical Power Year Period (x) Demand x2 xy 1999 1 74 1 74 2000 2 79 4 158 2001The trend3 line is 80 9 240 2002 4 90 16 360 2003 y^ 5= 56.86  xy .(7)(4)(98.86) b =  x2 .063 x=4 y = 98.bx = 98.54(4) = 56.(7)(42) = 10.70 + 10.54x 105 25 525 2004 6 142 36 852 2005 7 122 49 854  x = 28  y = 692  x2 = 140  xy = 3.

Least Squares Example 160 – Trend line. 150 – y^ = 56. Inc.70 + 10.54x 140 – Power demand 130 – 120 – 110 – 100 – 90 – 80 – 70 – 60 – 50 – | | | | | | | | | 1999 2000 2001 2002 2003 2004 2005 2006 2007 Year © 2006 Prentice Hall. 4 – 77 .

Find average historical demand for each season 2. Compute the average demand over all seasons 3. Inc. then multiply it by the seasonal index for that season © 2006 Prentice Hall. Seasonal Variations In Data The multiplicative seasonal model can modify trend data to accommodate seasonal variations in demand 1. 4 – 79 . Estimate next year’s total demand 5. Divide this estimate of total demand by the number of seasons. Compute a seasonal index for each season 4.

4 – 80 . Seasonal Index Example Demand Average Average Seasonal Month 2003 2004 2005 2003-2005 Monthly Index Jan 80 85 105 90 94 Feb 70 85 85 80 94 Mar 80 93 82 85 94 Apr 90 95 115 100 94 May 113 125 131 123 94 Jun 110 115 120 115 94 Jul 100 102 113 105 94 Aug 88 102 110 100 94 Sept 85 90 95 90 94 Oct 77 78 85 80 94 Nov 75 72 83 80 94 Dec 82 78 80 80 94 © 2006 Prentice Hall. Inc.

Inc.957 123 94 Jun 110 115 120 115 94 Jul 100 102 113 105 94 Aug 88 102 110 100 94 Sept 85 90 95 90 94 Oct 77 78 85 80 94 Nov 75 72 83 80 94 Dec 82 78 80 80 94 © 2006 Prentice Hall.957 Feb 70 85 85 80 94 Mar 80 93 average 82 2003-2005 85 monthly demand 94 Seasonal index = Apr 90 95 115 average monthly 100 demand94 May 113 125= 90/94 131 = . Seasonal Index Example Demand Average Average Seasonal Month 2003 2004 2005 2003-2005 Monthly Index Jan 80 85 105 90 94 0. 4 – 81 .

904 Apr 90 95 115 100 94 1. Inc.223 Jul 100 102 113 105 94 1.957 Oct 77 78 85 80 94 0. 4 – 82 .851 Nov 75 72 83 80 94 0. Seasonal Index Example Demand Average Average Seasonal Month 2003 2004 2005 2003-2005 Monthly Index Jan 80 85 105 90 94 0.064 Sept 85 90 95 90 94 0.117 Aug 88 102 110 100 94 1.851 © 2006 Prentice Hall.309 Jun 110 115 120 115 94 1.851 Dec 82 78 80 80 94 0.957 Feb 70 85 85 80 94 0.851 Mar 80 93 82 85 94 0.064 May 113 125 131 123 94 1.

851 Nov 75 72 83 80 94 0. Seasonal Index Example Demand Average Average Seasonal Month 2003 2004 2005 2003-2005 Monthly Index Jan 80 85 105 90 94 0.309 Jun 110 115 120 1.200 115 94 1.904 Apr 90Expected 95 115annual demand 100 = 1. 4 – 83 .851 Mar 80 93 82 85 94 0.851 Dec 82 78 80 80 94 0.064 May 113 125 131 123 94 1.200 100 94 1.957 12 Oct 77 78 85 80 94 0.064 Sept 85 Feb 95 90 x90.223 Jan x .957 = 96 Jul 100 102 113 12 105 94 1.200 94 1.117 Aug 88 102 110 1. Inc.851 = 85 94 0.957 Feb 70 85 Forecast 85 for802006 94 0.851 © 2006 Prentice Hall.

Inc. 4 – 84 . Seasonal Index Example 2006 Forecast 140 – 2005 Demand 130 – 2004 Demand 120 – 2003 Demand Demand 110 – 100 – 90 – 80 – 70 – | | | | | | | | | | | | J F M A M J J A S O N D Time © 2006 Prentice Hall.

800 – 9745 9702 9616 9659 9. Inc.200 – 10. San Diego Hospital Trend Data 10.000 – | | | | | | | | | | | | Jan Feb Mar Apr May June July Aug Sept Oct Nov Dec 67 68 69 70 71 72 73 74 75 76 77 78 Month Figure 4.000 – Inpatient Days 9.200 – 9.6 © 2006 Prentice Hall.600 – 9573 9766 9530 9680 9723 9594 9637 9.400 – 9551 9. 4 – 85 .

94 – 0.96 0.99 0.02 1.97 0.7 © 2006 Prentice Hall.98 – 0.97 0.00 0.01 1.04 1.96 – 0.03 1.92 – | | | | | | | | | | | | Jan Feb Mar Apr May June July Aug Sept Oct Nov Dec 67 68 69 70 71 72 73 74 75 76 77 78 Month Figure 4.04 – 1.98 0. San Diego Hospital Seasonal Indices 1.04 Index for Inpatient Days 1.06 – 1. Inc.00 – 1. 4 – 86 .99 0.02 – 1.

8 © 2006 Prentice Hall. Inc.200 – 10068 10.200 – 9265 9355 9.800 – 9764 9724 9691 9. San Diego Hospital Combined Trend and Seasonal Forecast 10.600 – 9572 9.000 – 9949 9911 Inpatient Days 9.400 – 9520 9542 9411 9. 4 – 87 .000 – | | | | | | | | | | | | Jan Feb Mar Apr May June July Aug Sept Oct Nov Dec 67 68 69 70 71 72 73 74 75 76 77 78 Month Figure 4.

Associative Forecasting Used when changes in one or more independent variables can be used to predict the changes in the dependent variable Most common technique is linear regression analysis We apply this technique just as we did in the time series example © 2006 Prentice Hall. 4 – 88 . Inc.

Inc. Associative Forecasting Forecasting an outcome based on predictor variables using the least squares technique y^ = a + bx ^ where y = computed value of the variable to be predicted (dependent variable) a = y-axis intercept b = slope of the regression line x = the independent variable though to predict the value of the © 2006 Prentice Hall. dependent variable 4 – 89 .

x 2.0 1 3. y ($000.0 1 3.0 3 2. Associative Forecasting Example Sales Local Payroll ($000. Inc.000.0 – 1. 4 – 90 .0 – | | | | | | | 0 1 2 3 4 5 6 7 Area payroll © 2006 Prentice Hall.000).0 – 2.000).0 – 3.5 4 4.0 2 2.5 7 Sales 2.

0 2.nx2 = 80 .75 © 2006 Prentice Hall.5 ∑y = 15.0 2.5) x = ∑x/6 = 18/6 = 3 b= ∑x2 .0 3.5 4 16 10.5 . y Payroll.0 ∑x = 18 ∑x2 = 80 ∑xy = 51.0 2 4 4.0 3.(6)(3)(2.bx = 2.5 . Associative Forecasting Example Sales. 4 – 91 .0 3 9 9.0 2.5 ∑xy . Inc.5 7 49 24.25 y = ∑y/6 = 15/6 = 2.5 a = y .25)(3) = 1.nxy 51.0 1 1 2. x x2 xy 2.(.(6)(32) = .0 1 1 2.

75 + .25(payroll) If payroll next year 4.75 + .0 – is estimated to be 3.000 | | | | | | | 0 1 2 3 4 5 6 7 Area payroll © 2006 Prentice Hall. 4 – 92 .0 – Sales = 1. Inc.25 $600 million.0 – Sales = $325. Associative Forecasting Example y^ = 1.25x Sales = 1. then: 3.0 – Sales 2.75 + .25(6) 1.

0 – probability distribution 1.0 – actually the 3.25 3. 4 – 93 .9 © 2006 Prentice Hall. Inc.0 – mean of a Sales 2.0 – | | | | | | | 0 1 2 3 4 5 6 7 Area payroll Figure 4. Standard Error of the Estimate  A forecast is just a point estimate of a future value  This point is 4.

points 4 – 94 . Inc.x = n-2 where y = y-value of each data point yc = computed value of the dependent variable.yc)2 Sy. Standard Error of the Estimate ∑(y . from the regression equation n = number of data © 2006 Prentice Hall.

Standard Error of the Estimate Computationally. Inc.x = n-2 We use the standard error to set up prediction intervals around the point estimate © 2006 Prentice Hall. 4 – 95 . this equation is considerably easier to use ∑y2 .b∑xy Sy.a∑y .

0 – Sales The standard error 2. 4 – 96 .x = . Inc.0 – 3.x = = n-2 6-2 Sy.25(51.5) Sy.75(15) .b∑xy 39. Standard Error of the Estimate ∑y2 .a∑y .600 in sales | | | | | | | 0 1 2 3 4 5 6 7 Area payroll © 2006 Prentice Hall.1.0 – of the estimate is 1.0 – $30.5 ..25 3.306 4.

4 – 97 . measures degree of association  Values range from -1 to +1 © 2006 Prentice Hall. Correlation  How strong is the linear relationship between the variables?  Correlation does not necessarily imply causality!  Coefficient of correlation. r. Inc.

( x)2][n y2 . 4 – 98 . Inc. x y r= [n x2 .( y)2] © 2006 Prentice Hall. Correlation Coefficient n xy .

Inc.∑x∑y r= [n∑x2 . y Correlation Coefficient y n∑xy .(∑y)2] (a) Perfect positive x (b) Positive x correlation: correlation: r = +1 0<r<1 y y x (d) Perfect negative x (c) No correlation: r=0 correlation: r = -1 © 2006 Prentice Hall. 4 – 99 .(∑x)2][n∑y2 .

r2.901 r2 = . Correlation  Coefficient of Determination. Inc. 4 – 100 . measures the percent of change in y predicted by the change in x  Values range from 0 to 1  Easy to interpret For the Nodel Construction example: r = .81 © 2006 Prentice Hall.

linear regression can be extended to multiple regression to accommodate several independent variables ^ y = a + b1x1 + b2x2 … Computationally. computer 4 – 101 . this is quite complex and generally done on the © 2006 Prentice Hall. Multiple Regression Analysis If more than one independent variable is to be used in the model. Inc.

00 Sales = $300.0x y 1 2 An improved correlation coefficient of r = .80 + .96 means this model does a better job of predicting the change in construction sales Sales = 1.0(.000 © 2006 Prentice Hall. Multiple Regression Analysis In the Nodel example.30(6) . 4 – 102 .5.12) = 3.5.30x .80 + . including interest rates in the model gives the new equation: ^ = 1. Inc.

Inc. 4 – 103 . the forecast has a bias error © 2006 Prentice Hall. Monitoring and Controlling Forecasts Tracking Signal  Measures how well the forecast is predicting actual values  Ratio of running sum of forecast errors (RSFE) to mean absolute deviation (MAD)  Good tracking signal has low values  If forecasts are continually high or low.

Monitoring and Controlling
Forecasts

Tracking = RSFE
signal MAD

∑(actual demand in
period i -
forecast demand
Tracking = in period i)
signal  ∑|actual - forecast|/n)

© 2006 Prentice Hall, Inc. 4 – 104

Tracking Signal
Signal exceeding limit
Tracking signal
Upper control limit
+

0 MADs Acceptable
range

Lower control limit

Time

© 2006 Prentice Hall, Inc. 4 – 105

Tracking Signal Example
Cumulative
Absolute Absolute
Actual Forecast Forecast Forecast
Qtr Demand Demand Error RSFE Error Error MAD

1 90 100 -10 -10 10 10 10.0
2 95 100 -5 -15 5 15 7.5
3 115 100 +15 0 15 30 10.0
4 100 110 -10 -10 10 40 10.0
5 125 110 +15 +5 15 55 11.0
6 140 110 +30 +35 30 85 14.2

© 2006 Prentice Hall, Inc. 4 – 106

Tracking Signal Example Cumulative Tracking Absolute Absolute Actual Signal Forecast Forecast Forecast Qtr (RSFE/MAD) Demand Demand Error RSFE Error Error MAD 1 90-10/10 100= -1 -10 -10 10 10 10.0 4 100-10/10 110= -1 -10 -10 10 40 10.2 110= +2.5+15 +5 15 55 11. 4 – 107 .5 +30 +35 30 85 14.0 2 95 -15/7.5 3 115 0/10 100= 0 +15 0 15 30 10. Inc.0 6 140 +35/14.5 100= -2 -5 -15 5 15 7.5 is within acceptable limits © 2006 Prentice Hall.0 5 125 +5/11110 = +0.0 and +2.2 The variation of the tracking signal between -2.

Inc. 4 – 108 . Adaptive Forecasting It’s possible to use the computer to continually monitor forecast error and adjust the values of the  and  coefficients used in exponential smoothing to continually minimize forecast error This technique is called adaptive smoothing © 2006 Prentice Hall.

Inc. There is no single techniques that should be used for all products or services This approach uses historical data to test multiple forecasting models for individual items The forecasting model with the lowest error is then used to forecast the next demand © 2006 Prentice Hall. 4 – 109 . Focus Forecasting Developed at American Hardware Supply. focus forecasting is based on two principles: 1. Sophisticated forecasting models are not always better than simple models 2.

Inc. Forecasting in the Service Sector  Presents unusual challenges  Special need for short term records  Needs differ greatly as function of industry and product  Holidays and other calendar events  Unusual events © 2006 Prentice Hall. 4 – 110 .

Inc. 4 – 111 .12 © 2006 Prentice Hall. Fast Food Restaurant Forecast 20% – Percentage of sales 15% – 10% – 5% – 11-12 1-2 3-4 5-6 7-8 9-10 12-1 2-3 4-5 6-7 8-9 10-11 (Lunchtime) (Dinnertime) Hour of day Figure 4.