1. Portland State University Operations Management BA 339 Instructor: Scott Culbertson Jan 14th - Forecasting

2. Portland State University Varsity Subs Process Order Prep Sandwich Put in Oven Bake Toppings Counter Time Wrap & Deliver CT = 1 CT = 4CT = 1CT = 8 CT = 3CT = 7CT = 2 Q1

3. Portland State University Throughput? Process Order Prep Sandwich Put in Oven Bake Toppings Counter Time Wrap & Deliver CT = 1 CT = 4CT = 1CT = 8 CT = 3CT = 7CT = 2 Harry - Sam - Oven - Counter -

4. Portland State University Throughput? Process Order Prep Sandwich Put in Oven Bake Toppings Counter Time Wrap & Deliver CT = 1 CT = 4CT = 1CT = 8 CT = 3CT = 7CT = 2 Harry - 1/5 minutes or 12/hour Sam - 1/6 minutes or 10/hour - Constraint! Oven - 10/8 minutes or 75 hour Counter - Unlimited

5. Portland State University Varsity Subs How many subs in 4 hours? The easy answer is to look at the most constrained throughput of Sam (10 per hour). The answer then becomes 40 (4*10). However, the other logical conclusion is to say that the first 26 minutes of operation in the morning only yields 1 sub. Therefor, total time remaining would be 4*60 = 240 Minutes total 240 – 26 = 214 After 26 minutes, the rate is 10/hour. Therefor, they can produce 214/60*10 = 35.66 subs. 35.66 + 1 (from the first 26 minutes) = 36.66 On the test, either answer would be acceptable (40 or 36.66) as long as you state your assumptions.

6. Portland State University Dimensions of Strategic Competitive Advantage Innovator Operations Efficiency Customer Intimacy

7. Portland State University Dimensions of Operations Strategy & Competitive Advantage Time Price Quality Variety Competitive Advantage & Profit Means to best satisfy the customer

8. Portland State University Understand Key Relationships Understand Key Relationships Time Price Quality Variety Dimensions of Competitive AdvantageKey Elements of OPS Inventory Capacity Cycle Time

9. Portland State University How does Forecast Accuracy impact the key dimensions of Competitive Advantage?

10. Portland State University Financial impact: Inventory excursions create incremental cost and lost opportunity. Inventory’s Financial Impact Stockouts begin to occur before inventory hits zero. Lost sales occur until SC adjusts. Channel dries up, marketing momentum is lost. time Product Life Cycle Inventory Profile over Product Life Cycle Inventory Level - W.O.S. Initial Desired Inventory Level (ex: 4 WOS) Very high inventory. High carrying costs (component depreciation, capital cost). Very high inventory risk (time-to-consumption is high). A C B Excess inventory at end-of- life creates clearance discounts, price protection. Impacts pricing of next product. Impacts time-to-market of next product.

11. Portland State University Business goal: maximize total contribution margin over the life-cycle of a product. Cumulative Contribution

12. Portland State University Responsiveness of a supply chain is manifest in the height and duration of inventory excursions. Shorter supply chains are more robust to demand surprises. Supply Chain Response

13. Portland State University Shorter supply chains are more robust to demand surprises. Impact of Flow Time H.O.

14. Portland State University Learning Objectives After studying this chapter you should be able to:   Identify or Define :   Forecasting   Types of forecasts   Time horizons   Approaches to forecasts

15. Portland State University Learning Objectives - continued When you complete this chapter, you should be able to :  Understand and Use:  Moving averages  Exponential smoothing  Trend projections  Regression and correlation analysis  Measures of forecast accuracy

16. Portland State University What is Forecasting?   Process of predicting a future event   Underlying basis of all business decisions   Production   Inventory   Personnel   Facilities Sales will be $200 Million!

17. Portland State University  Short-range forecast  Up to 1 year; usually less than 3 months  Job scheduling, Procurement,worker assignments  Medium-range forecast  3 months to 3 years  Sales & production planning, budgeting  Long-range forecast  3+ years  New product planning, facility location Types of Forecasts by Time Horizon

18. Portland State University Influence of Product Life Cycle  Stages of introduction and growth require longer forecasts than maturity and decline  Forecasts useful in projecting  staffing levels,  inventory levels, and  factory capacity as product passes through life cycle stages

19. Portland State University Strategy and Issues During a Product’s Life IntroductionGrowth Maturity Decline Standardization Less rapid product changes - more minor changes Optimum capacity Increasing stability of process Long production runs Product improvement and cost cutting Little product differentiation Cost minimization Over capacity in the industry Prune line to eliminate items not returning good margin Reduce capacity Forecasting critical Product and process reliability Competitive product improvements and options Increase capacity Shift toward product focused Enhance distribution Product design and development critical Frequent product and process design changes Short production runs High production costs Limited models Attention to quality Best period to increase market share R&D product engineering critical Practical to change price or quality image Strengthen niche Cost control critical Poor time to change image, price, or quality Competitive costs become critical Defend market position OM Strategy/Issues Company Strategy/Issues HDTV CD-ROM Color copiers Drive-thru restaurants Fax machines Station wagons Sales 3 1/2” Floppy disks Internet

20. Portland State University Product Demand Charted over 4 Years with Trend and Seasonality Year 1 Year 2 Year 3 Year 4 Seasonal peaksTrend component Actual demand line Average demand over four years Demand for product or service Random variation

21. Portland State University Realities of Forecasting  Forecasts are seldom perfect  Most forecasting methods assume that there is some underlying stability in the system  Both product family and aggregated product forecasts are more accurate than individual product forecasts

22. Portland State University Forecasting Approaches   Used when situation is ‘stable’ & historical data exist   Existing products   Current technology   Involves mathematical techniques   e.g., forecasting sales of color televisions Quantitative Methods   Used when situation is vague & little data exist   New products   New technology   Involves intuition, experience   e.g., forecasting sales on Internet Qualitative Methods

23. Portland State University Overview of Qualitative Methods  Jury of executive opinion  Pool opinions of high-level executives, sometimes augment by statistical models  Sales force composite  Estimates from individual salespersons are reviewed for reasonableness, then aggregated  Delphi method  Panel of experts, queried iteratively  Consumer Market Survey  Ask the customer

24. Portland State University Quantitative Forecasting Methods (Non-Naive) Quantitative Forecasting Linear Regression Associative Models Exponential Smoothing Moving Average Time Series Models Trend Projection

25. Portland State University  Persistent, overall upward or downward pattern  Due to population, technology etc.  Several years duration Mo., Qtr., Yr. Response © 1984-1994 T/Maker Co. Trend Component

26. Portland State University  Regular pattern of up & down fluctuations  Due to weather, customs etc.  Occurs within 1 year Mo., Qtr. Response Summer © 1984-1994 T/Maker Co. Seasonal Component

27. Portland State University  Repeating up & down movements  Due to interactions of factors influencing economy  Usually 2-10 years duration Mo., Qtr., Yr. Response Cycle  Cyclical Component

28. Portland State University  Erratic, unsystematic, ‘residual’ fluctuations  Due to random variation or unforeseen events  Union strike  Tornado  Short duration & nonrepeating © 1984-1994 T/Maker Co. Random Component

29. Portland State University Naive Approach   Assumes demand in next period is the same as demand in most recent period   e.g., If May sales were 48, then June sales will be 48   Sometimes cost effective & efficient   Responds very quickly © 1995 Corel Corp.

30. Portland State University  MA is a series of arithmetic means  Used if little or no trend  Used often for smoothing  Provides overall impression of data over time  Equation MA n n  Demand in Previous Periods Periods Moving Average Method

31. Portland State University You’re manager of a museum store that sells historical replicas. You want to forecast sales (000) for 1998 using a 3-period moving average. 19934 1994 6 19955 19963 19977 © 1995 Corel Corp. Moving Average Example

32. Portland State University Moving Average Solution

33. Portland State University Moving Average Solution

34. Portland State University Moving Average Solution

35. Portland State University 959697989900 Year Sales 2 4 6 8 Actual Forecast Moving Average Graph

36. Portland State University  Used when trend is present  Older data usually less important  Weights based on intuition  Often lay between 0 & 1, & sum to 1.0  Equation WMA = Σ(Weight for period n) (Demand in period n) ΣWeights Weighted Moving Average Method

37. Portland State University Actual Demand, Moving Average, Weighted Moving Average Actual sales Moving average Weighted moving average

38. Portland State University

40.  Increasing n makes forecast less sensitive to changes  Do not forecast trend well © 1984-1994 T/Maker Co. Disadvantages of Moving Average Methods

41. Portland State University  Form of weighted moving average  Weights decline exponentially  Most recent data weighted most  Requires smoothing constant (  )  Ranges from 0 to 1  Subjectively chosen Exponential Smoothing Method

42. Portland State University  F t =  A t - 1 +  (1-  ) A t - 2 +  (1-  ) 2 ·A t - 3 +  (1-  ) 3 A t - 4 +... +  (1-  ) t- 1 ·A 0  F t = Forecast value  A t = Actual value   = Smoothing constant  F t = F t -1 +  ( A t -1 - F t -1 )  Use for computing forecast Exponential Smoothing Equations

43. Portland State University You’re organizing a Kwanza meeting. You want to forecast attendance for 2000 using exponential smoothing (  =.10). The1995 forecast was 175. 1995180 1996 168 1997159 1996175 1999190 © 1995 Corel Corp. Exponential Smoothing Example

44. Portland State University F t = F t -1 +  ·  ( A t -1 - F t -1 ) Time Actual Forecast, F t ( α =.10) 1995 180175.00 (Given) 1996168 1997159 1998175 1999190 2000NA 175.00 + Exponential Smoothing Example

45. Portland State University F t = F t -1 +  ·  ( A t -1 - F t -1 ) Time Actual Forecast, F t ( α =.10) 1995180 175.00 (Given) 1996168 175.00 +.10( 1997159 1998175 1999190 2000NA Exponential Smoothing Example

46. Portland State University F t = F t -1 +  ·  ( A t -1 - F t -1 ) TimeActual Forecast,F t ( α =.10) 1995180 175.00 (Given) 1996168 175.00 +.10(180 - 1997159 1998175 1999190 2000NA Exponential Smoothing Example

47. Portland State University F t = F t -1 +  ·  ( A t -1 - F t -1 ) TimeActual Forecast,F t ( α =.10) 1995180 175.00 (Given) 1996168 175.00 +.10(180 - 175.00) 1997159 1998175 1999190 2000NA Exponential Smoothing Example

48. Portland State University F t = F t -1 +  ·  ( A t -1 - F t -1 ) TimeActual Forecast,F t ( αααα =.10) 1995180 175.00 (Given) 1996168 175.00 +.10(180 - 175.00) = 175.50 1997159 1998175 1999190 2000NA Exponential Smoothing Example

49. Portland State University F t = F t -1 +  ·  ( A t -1 - F t -1 ) TimeActual Forecast, F t ( α =.10) 1995180175.00 (Given) 1994168 175.00 +.10(180 - 175.00) = 175.50 1995159 175.50 +.10(168 - 175.50) = 174.75 1996175 1997190 1998NA Exponential Smoothing Example

50. Portland State University F t = F t -1 +  ·  ( A t -1 - F t -1 ) TimeActual Forecast, F t ( α =.10) 1995180 175.00 (Given) 1996168175.00 +.10(180 - 175.00) = 175.50 1997159 175.50 +.10(168 - 175.50) = 174.75 1998175 1999190 2000NA 174.75 +.10(159 - 174.75)= 173.18 Exponential Smoothing Example

51. Portland State University F t = F t -1 +  ·  ( A t -1 - F t -1 ) TimeActual Forecast, F t ( α =.10) 1995180175.00 (Given) 1996168 175.00 +.10(180 - 175.00) = 175.50 1997159 175.50 +.10(168 - 175.50) = 174.75 1998 175 174.75 +.10(159 - 174.75) = 173.18 1999190 173.18 +.10(175 - 173.18) = 173.36 2000NA Exponential Smoothing Example

52. Portland State University F t = F t -1 +  ·  ( A t -1 - F t -1 ) TimeActual Forecast, F t ( α =.10) 1995180 175.00 (Given) 1996168 175.00 +.10(180 - 175.00) = 175.50 1997159 175.50 +.10(168 - 175.50) = 174.75 1998175 174.75 +.10(159 - 174.75) = 173.18 1999190 173.18 +.10(175 - 173.18) = 173.36 2000NA 173.36 +.10(190 - 173.36) = 175.02 Exponential Smoothing Example

53. Portland State University Year Sales 140 150 160 170 180 190 939495969798 Actual Forecast Exponential Smoothing Example

54. Portland State University F t =  A t - 1 +  (1-  ) A t - 2 +  (1-  ) 2 A t - 3 +... Forecast Effects of Smoothing Constant  Weights Prior Period  2 periods ago  (1 -  ) 3 periods ago  (1 -  ) 2 ==  = 0.10  = 0.90 10%

55. Portland State University F t =  A t - 1 +  (1-  ) A t - 2 +  (1-  ) 2 A t - 3 +... Weights Prior Period  2 periods ago  (1 -  ) 3 periods ago  (1 -  ) 2 ==  = 0.10  = 0.90 10% 9% Forecast Effects of Smoothing Constant 

56. Portland State University F t =  A t - 1 +  (1-  ) A t - 2 +  (1-  ) 2 A t - 3 +... Weights Prior Period  2 periods ago  (1 -  ) 3 periods ago  (1 -  ) 2 ==  = 0.10  = 0.90 10% 9% 8.1% Forecast Effects of Smoothing Constant 

57. Portland State University F t =  A t - 1 +  (1-  ) A t - 2 +  (1-  ) 2 A t - 3 +... Weights Prior Period  2 periods ago  (1 -  ) 3 periods ago  (1 -  ) 2 ==  = 0.10  = 0.90 10% 9% 8.1% 90% Forecast Effects of Smoothing Constant 

58. Portland State University F t =  A t - 1 +  (1-  ) A t - 2 +  (1-  ) 2 A t - 3 +... Weights Prior Period  2 periods ago  (1 -  ) 3 periods ago  (1 -  ) 2 ==  = 0.10  = 0.90 10% 9% 8.1% 90%9% Forecast Effects of Smoothing Constant 

59. Portland State University F t =  A t - 1 +  (1-  ) A t - 2 +  (1-  ) 2 A t - 3 +... Weights Prior Period  2 periods ago  (1 -  ) 3 periods ago  (1 -  ) 2 ==  = 0.10  = 0.90 10% 9% 8.1% 90%9%0.9% Spreadsheet Forecast Effects of Smoothing Constant 

60. Portland State University Choosing  Seek to minimize the Mean Absolute Deviation (MAD) If:Forecast error = demand - forecast Then:

61. Portland State University Exponential Smoothing with Trend Adjustment Forecast including trend (FIT t ) = exponentially smoothed forecast (F t ) + exponentially smoothed trend (T t )

62. Portland State University F t =  (Actual demand previous period) + (1-  )(Forecast last period+Trend estimate last period) F t =  (A t-1 ) + (1-  )(F t-1 + T t-1 ) or T t =  (Forecast this period - Forecast last period) + (1-  )(Trend estimate last period T t =  (F t - F t-1 ) + (1-  )T t-1 or Exponential Smoothing with Trend Adjustment

63. Portland State University  F t = exponentially smoothed forecast of the data series in period t  T t = exponentially smoothed trend in period t  A t = actual demand in period t  = smoothing constant for the average  = smoothing constant for the trend Exponential Smoothing with Trend Adjustment

64. Portland State University Comparison of Forecasts Actual Demand Exponential smoothing Exponential smoothing + Trend

65. Portland State University Least Squares Deviation Time Values of Dependent Variable Actual observation Point on regression line

66. Portland State University Actual and the Regression Line Actual demand Y = 56.70+ 10.54X

67. Portland State University  Used for forecasting linear trend line  Assumes relationship between response variable, Y, and time, X, is a linear function  Estimated by least squares method  Minimizes sum of squared errors  i YabX i  Linear Trend Projection

68. Portland State University b > 0 b < 0 a a Y Time, X Linear Trend Projection

69. Portland State University Time Sales 0 0 1 1 2 2 3 3 4 4 9293949596 Sales vs. Time Scatter Diagram

70. Portland State University Least Squares Equations Equation: Slope: Y-Intercept: print

71. Portland State University You’re a marketing analyst for Hasbro Toys. You gather the following data: YearSales (Units) 19951 19961 19972 19982 19994 What is the trend equation? Linear Trend Projection Example

72. Portland State University You’re a marketing analyst for Hasbro Toys. Using coded years, you find Y i = -.1 +.7X i. YearSales (Units) 19951 19961 19972 19982 19994 Forecast 2000 sales. ^ Linear Trend Projection Example Article

73. Portland State University Linear Regression Equations Equation: Slope: Y-Intercept:

74. Portland State University  Slope ( b )  Estimated Y changes by b for each 1 unit increase in X  If b = 2, then sales ( Y ) is expected to increase by 2 for each 1 unit increase in advertising ( X )  Y-intercept ( a )  Average value of Y when X = 0  If a = 4, then average sales ( Y ) is expected to be 4 when advertising ( X ) is 0 Interpretation of Coefficients

75. Portland State University Measures

76. Text uses symbol Y c Standard Error of the Estimate (standard deviation) What is the expected distribution around the regression line? sp

77. Portland State University  Answers: ‘ how strong is the linear relationship between the variables?’  Coefficient of correlation Sample correlation coefficient denoted r  Values range from -1 to +1  Measures degree of association  Used mainly for understanding Correlation

78. Portland State University Sample Coefficient of Correlation

79. Portland State University +1.00 Perfect Positive Correlation Increasing degree of negative correlation -.5+.5 Perfect Negative Correlation No Correlation Increasing degree of positive correlation Coefficient of Correlation Values

80. Portland State University Coefficient of Correlation and Regression Model

81. Portland State University  You want to achieve:  No pattern or direction in forecast error  Error = ( Y i - Y i ) = (Actual - Forecast)  Seen in plots of errors over time  Smallest forecast error  Mean square error (MSE)  Mean absolute deviation (MAD) Guidelines for Selecting Forecasting Model ^

82. Portland State University Time (Years) Error 0 0 Desired Pattern Time (Years) Error 0 Trend Not Fully Accounted for Pattern of Forecast Error

83. Portland State University  Mean Square Error (MSE)  Mean Absolute Deviation (MAD) Forecast Error Equations

84. Portland State University You’re a marketing analyst for Hasbro Toys. You’ve forecast sales with a linear model & exponential smoothing. Which model do you use? ActualLinear ModelExponential Smoothing YearSalesForecastForecast (.9) 199510.61.0 199611.31.0 199722.01.9 199822.72.0 199943.43.8 Selecting Forecasting Model Example

85. Portland State University Linear Model Evaluation

86. Portland State University Exponential Smoothing Model Evaluation

87. Portland State University Exponential Smoothing Model Evaluation Linear Model: MSE = Σ Error 2 / n = 1.10 / 5 =.220 MAD = Σ |Error| / n = 2.0 / 5 =.400 Exponential Smoothing Model: MSE = Σ Error 2 / n = 0.05 / 5 = 0.01 MAD = Σ |Error| / n = 0.3 / 5 = 0.06

88. Portland State University  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  Should be within upper and lower control limits Tracking Signal

89. Portland State University Tracking Signal Running Sum Forecast Error

90. Portland State University Tracking Signal

91. Portland State University Tracking Signal

92. Portland State University Tracking Signal

93. Portland State University Tracking Signal

94. Portland State University Tracking Signal

95. Portland State University Tracking Signal

96. Portland State University Tracking Signal

97. Portland State University Tracking Signal

98. Portland State University Tracking Signal

99. Portland State University Tracking Signal

100. Portland State University Tracking Signal

101. Portland State University Tracking Signal

102. Portland State University Tracking Signal

103. Portland State University Plot of a Tracking Signal Time Lower control limit Upper control limit Signal exceeded limit Tracking signal Acceptable range MAD + 0 -