1 / 84

Introduction to Forecasting

Introduction to Forecasting. COB 291 Spring 2000. Forecasting. A forecast is an estimate of future demand Forecasts contain error Forecasts can be created by subjective means by estimates from informal sources OR forecasts can be determined mathematically by using historical data

iokina
Télécharger la présentation

Introduction to Forecasting

An Image/Link below is provided (as is) to download presentation Download Policy: Content on the Website is provided to you AS IS for your information and personal use and may not be sold / licensed / shared on other websites without getting consent from its author. Content is provided to you AS IS for your information and personal use only. Download presentation by click this link. While downloading, if for some reason you are not able to download a presentation, the publisher may have deleted the file from their server. During download, if you can't get a presentation, the file might be deleted by the publisher.

E N D

Presentation Transcript


  1. Introduction to Forecasting COB 291 Spring 2000

  2. Forecasting • A forecast is an estimate of future demand • Forecasts contain error • Forecasts can be created by subjective means by estimates from informal sources • OR forecasts can be determined mathematically by using historical data • OR forecasts can be based on both subjective and mathematical techniques.

  3. Qualitative Approaches • Executive committee consensus • Delphi method • Survey of sales force • Survey of customers • Historical analogy • Market research

  4. Quantitative Approaches • Based on the assumption that the “forces” that generated the past demand will generate the future demand (i.e., history will tend to repeat itself) • Analysis of the past demand pattern provides a good basis for forecasting future demand

  5. Quantitative Approaches • Simple Linear Regression • Relationship between one independent variable, x, and a dependent variable, y • Assumed to be linear • Form: Y=a+bX • Y=dependent variable • a=y-intercept • X=independent variable • b=slope of the regression line

  6. Quantitative Methods - L.S. Regression Example Perfect Lawns, Inc., intends to use sales of lawn fertilizer to predict lawn mower sales. The store manager feels that there is probably a six-week lag between fertilizer sales and mower sales. The pertinent data are shown below. =>

  7. Quantitative Methods - L.S. Regression Example Period Fertilizer Sales Number of Mowers Sold (Tons) (Six-Week Lag) 1 1.7 11 2 1.4 9 3 1.9 11 4 2.1 13 5 2.3 14 6 1.7 10 7 1.6 9 8 2 13 9 1.4 9 10 2.2 16 11 1.5 10 12 1.7 10 A) Use the least squares method to obtain a linear regression line for the data.

  8. Quantitative Methods - L.S. Regression Example Period Fertilizer Sales Number of Mowers Sold (X) (Y) X2 Y2 (Tons) (X) (Six-Week Lag) (Y) 1 1.7 11 18.7 2.89 121 2 1.4 9 12.6 1.96 81 3 1.9 11 20.9 3.61 121 4 2.1 13 27.3 4.41 169 5 2.3 14 32.2 5.29 196 6 1.7 10 17.0 2.89 100 7 1.6 9 14.4 2.56 81 8 2 13 26.0 4.00 169 9 1.4 9 12.6 1.96 81 10 2.2 16 35.2 4.84 256 11 1.5 10 15.0 2.25 100 12 1.7 10 17.0 2.89 100

  9. Quantitative Methods - L.S. Regression Example Period Fertilizer Sales Number of Mowers Sold (X) (Y) X2 Y2 (Tons) (X) (Six-Week Lag) (Y) 1 1.7 11 18.7 2.89 121 2 1.4 9 12.6 1.96 81 3 1.9 11 20.9 3.61 121 4 2.1 13 27.3 4.41 169 5 2.3 14 32.2 5.29 196 6 1.7 10 17.0 2.89 100 7 1.6 9 14.4 2.56 81 8 2 13 26.0 4.00 169 9 1.4 9 12.6 1.96 81 10 2.2 16 35.2 4.84 256 11 1.5 10 15.0 2.25 100 12 1.7 10 17.0 2.89 100 SUM 21.5 135 248.9 39.55 1575

  10. Quantitative Methods - L.S. Regression Example

  11. Quantitative Methods - L.S. Regression Example

  12. Quantitative Methods - L.S. Regression Example

  13. Quantitative Methods - L.S. Regression Example

  14. Time Series Analysis • A time series is a set of numbers where the order or sequence of the numbers is important, e.g., historical demand • Analysis of the time series identifies patterns • Once the patterns are identified, they can be used to develop a forecast

  15. Time Series Models • Simple moving average • Weighted moving average • Exponential smoothing (exponentially weighted moving average) • Exponential smoothing with random fluctuations • Exponential smoothing with random and trend • Exponential smoothing with random and seasonal component

  16. Time Series Models Simple Moving Average Sample Data (3-period moving average) t Dt Ft Dt-Ft | Dt-Ft | Quarter Actual Demand Forecast Error Error 1 100 2 110 3 110 4 ? (100+110+110)/3=106.67

  17. Time Series Models Simple Moving Average Sample Data (3-period moving average) t Dt Ft Dt-Ft | Dt-Ft | Quarter Actual Demand Forecast Error Error 1 100 2 110 3 110 4 80 (100+110+110)/3=106.67 80-106.67=-26.67 26.67

  18. Time Series Models Simple Moving Average Sample Data (3-period moving average) t Dt Ft Dt-Ft | Dt-Ft | Quarter Actual Demand Forecast Error Error 1 100 2 110 3 110 4 80 (100+110+110)/3=106.67 80-106.67=-26.67 26.67 5 ? (110+110+80)/3 = 100.00

  19. Time Series Models Simple Moving Average Sample Data (3-period moving average) t Dt Ft Dt-Ft | Dt-Ft | Quarter Actual Demand Forecast Error Error 1 100 2 110 3 110 4 80 (100+110+110)/3=106.67 80-106.67=-26.67 26.67 5 100 (110+110+80)/3 = 100.00 0 0

  20. Time Series Models Exponential smoothing (exponentially weighted moving average)

  21. Time Series Models Exponential smoothing (exponentially weighted moving average) Where t=time period St=smoothed average at end of period t Dt=actual demand in period t a=smoothing constant (0<a<1) Ft=forecast for period t

  22. Time Series Models Exponential smoothing (exponentially weighted moving average) Sample Data (alpha = 0.2) t Dt St Ft Dt-Ft Quarter Actual Demand Smoothed Average Forecast Error 0 100

  23. Time Series Models Exponential smoothing (exponentially weighted moving average) Sample Data (alpha=0.2) t Dt St Ft Dt-Ft Quarter Actual Demand Smoothed Average Forecast Error 0 100 1 ? 100

  24. Time Series Models Exponential smoothing (exponentially weighted moving average) Sample Data (alpha=0.2) t Dt St Ft Dt-Ft Quarter Actual Demand Smoothed Average Forecast Error 0 100 1 100 100

  25. Time Series Models Exponential smoothing (exponentially weighted moving average) Sample Data (alpha=0.2) t Dt St Ft Dt-Ft Quarter Actual Demand Smoothed Average Forecast Error 0 100 1 100 100 100-100=0

  26. Time Series Models Exponential smoothing (exponentially weighted moving average) Sample Data (alpha=0.2) t Dt St Ft Dt-Ft Quarter Actual Demand Smoothed Average Forecast Error 0 100 1 100 .2(100)+.8(100)=100 100 100-100=0

  27. Time Series Models Exponential smoothing (exponentially weighted moving average) Sample Data (alpha=0.2) t Dt St Ft Dt-Ft Quarter Actual Demand Smoothed Average Forecast Error 0 100 1 100 .2(100)+.8(100)=100 100 100-100=0 2 ? 100

  28. Time Series Models Exponential smoothing (exponentially weighted moving average) Sample Data (alpha=0.2) t Dt St Ft Dt-Ft Quarter Actual Demand Smoothed Average Forecast Error 0 100 1 100 .2(100)+.8(100)=100 100 100-100=0 2 110 100 110-100=10

  29. Time Series Models Exponential smoothing (exponentially weighted moving average) Sample Data (alpha=0.2) t Dt St Ft Dt-Ft Quarter Actual Demand Smoothed Average Forecast Error 0 100 1 100 .2(100)+.8(100)=100 100 100-100=0 2 110 .2(110)+.8(100)=102 100 110-100=10

  30. Time Series Models Exponential smoothing (exponentially weighted moving average) Sample Data (alpha=0.2) t Dt St Ft Dt-Ft Quarter Actual Demand Smoothed Average Forecast Error 0 100 1 100 .2(100)+.8(100)=100 100 100-100=0 2 110 .2(110)+.8(100)=102 100 110-100=10 3 ? 102

  31. Time Series Models Exponential smoothing (exponentially weighted moving average) Sample Data (alpha=0.2) t Dt St Ft Dt-Ft Quarter Actual Demand Smoothed Average Forecast Error 0 100 1 100 .2(100)+.8(100)=100 100 100-100=0 2 110 .2(110)+.8(100)=102 100 110-100=10 3 110 102 110-102=8 Make forecasts for periods 4-12.

  32. Time Series Models Forecast Error 2 error measures: Bias tells direction (i.e., over or under forecast) Mean Absolute Deviation tells magnitude of forecast error

  33. Characteristics of Good Forecasts • Stability • Responsiveness • Data Storage Requirements

  34. BESM Example Cont’d

  35. BESM - Expanded • The Basic Exponential Smoothing Model (BESM) is nothing more than a cumulative weighted average of all past demand (and the initial smoothed average). • Proof:

  36. Demand Data with Trend

  37. Time Series Models Exponential smoothing with trend enhancement

  38. Demand Data with Trend and Seasonality

  39. Basic Model Applicationbase smoothing constant, alpha, =.20

  40. Trend-Enhanced Applicationbase smoothing constant, alpha, = .20 and trend smoothing constant, beta, = .30

  41. Seasonal Indexes • seasonal index = actual demand / average demand • divide demand by its seasonal index to deseasonalize and • multiply demand by its seasonal index to seasonalize.

  42. Full Model for Exponential Smoothing • NOTE: This model will allow you to forecast with trend only, with trend and seasonality, with seasonality only, or with no trend and no seasonality.

  43. Full Model for Exponential Smoothing (cont’d)

More Related