Business Forecasting Techniques Business Forecasting Chapter 2 by obm18412

VIEWS: 184 PAGES: 30

More Info
									  Business Forecasting

         Chapter 2
Data Patterns and Choice of
  Forecasting Techniques
                Chapter Topics

   Data Patterns

   Forecasting Methodologies

   Technique Selection

   Model Evaluation
          Data Pattern and Choice of

   The pattern of data

   The nature of the past relationship in the data

   The level of subjectivity in making a forecast

All of the above help us in how we classify the
  forecasting technique.
            Data Pattern and Choice of

   Univariate forecasting techniques depend on:
       Past data patterns.

   Multivariate forecasting techniques depend on
       Past relationships.

   Qualitative forecasts depend on:
       Subjectivity: Forecasters intuition.
                     Data Patterns
   Data Patterns as a Guide

       Simple observation of the data will show the way
        that data have behaved over time.

       Data pattern may suggest the existence of a
        relationship between two or more variables.

       Four Patterns: Horizontal, Trend, Seasonal, Cyclical.
                            Data Patterns

   Horizontal
       When there is no trend in the data pattern, we
        deal with horizontal data pattern.
        Forecast Variable


                    Data Patterns

   Trend
       Long-term growth movement of a time series

                      Trend       Yt   Trend

                              t                t

            Yt      Trend         Yt

                              t                t
                            Data Patterns
   Seasonal Pattern
       A predictable and repetitive movement observed
        around a trend line within a period of 1 year or
        Forecast Variable

                     Data Patterns

   Cyclical

       Occurs with business and economic expansions
        and contractions.

       Lasts longer than 1 year.

       Correlated with business cycles.
                Other Data Patterns
   Autocorrelated Pattern
       Data in one period are related to their values in
        the previous period.

       Generally, if there is a high positive autocorrelation,
        the value in the month of June, for example, is
        positively related to the values in the month of

       This pattern is more fully discussed when we talk
        about the Box–Jenkins methodology.
    Measures of Accuracy in Forecasting

       Error in Forecasting
                 et  Yt  Yt
       Measures the average error that can be expected
        over time.
       The average error concept has some problems
        with it. The positive and negative values cancel
        each other out and the mean is very likely to be
        close to zero.
           Error in Forecasting

   Mean Average Deviation (MAD)


                        e        t
              MAD       t 1
           Error in Forecasting

   Mean Square Error (MSE)


                  t 1
                          (e t )
       MSE 
           Error in Forecasting
   Mean Absolute Percentage Error

                           (et / Yt ) 100
        MAPE      t 1
            Error in Forecasting
   Mean Percentage Error

                     (e
                     t 1
                            t   / Yt )
           MPE 
   No bias, MPE should be zero.
             Evaluating Reliability

   Forecasters use the following two approaches
    to determine if the forecast is reliable or not:
       Root Mean Square (RMS)


                          t 1
                                 e t2
                 RMS 
          Evaluating Reliability

   Root Percent Mean Square (R%MS)


                    t 1
                           (e t2 / Yt )
         R % MS 
          Forecasting Methodologies
   Forecasting methodologies fall into three
       Quantitative Models

       Qualitative Models

       Technological Approaches
          Forecasting Methodologies
   Quantitative Models
       Also known as statistical models.

       Include time series and regression approaches.

       Forecast future values entirely on the historical
        observation of a variable.
         Forecasting Methodologies
   Quantitative Models
       An example of a quantitative model is shown
               Yt 1   0  1Yt   2Yt 1
        Yt 1= Sales one time period into the future

          Yt   = Sales in the current period

        Yt 1 = Sales in the last period
          Forecasting Methodologies
   Qualitative Models
       Non-statistical or judgment models

       Expert opinion

       Executive opinion

       Sale force composite forecast

       Focus groups

       Delphi method
          Forecasting Methodologies
   Technological Approach
       Combines quantitative and qualitative methods.

       The objective of the model is to combine
        technological, societal, political, and economic
                      Technique Selection
   Forecasters depend on:
       The characteristics of the decision making situation
        which may include:
            Time horizon

            Planning vs. control

            Level of detail

            Economic conditions in the market (stability vs. state of flux)
                  Technique Selection
   Forecasters depend on:
       The characteristics of the forecasting method
            Forecast horizon

            Pattern of data

            Type of model

            Costs associated with the model

            Level of accuracy and ease of application
                  Model Evaluation
   Forecasters depend on:
       The level of error associated with each model.

       Error is computed and looked at graphically.

       Control charts are used for model evaluations.

       Turning point diagram is used to evaluate a model.
               Model Evaluation
   A pattern of cumulative errors moving
    systematically away from zero in either
    direction is a signal that the model is
    generating biased forecasts.
   Management has to establish the upper and
    lower control limits.
   One fairly common rule of thumb is that the
    control limits are equal to 2 or 3 time the
    standard error.
                         Model Evaluation

Cumulative Error

                    10                      Model A
                     5                      Model B
                     0                      Model C
                    -5                      Model D
                Model Evaluation

Actual Change
                                                         Line of Perfect Forecast
     II–Turning Point Error     IB–Underestimate
     Prediction of downturn     of Positive
     that did not occur; or     change
     failure to predict an                    IA–Overestimate
     upturn                                 of Positive change

    IIIA–Overestimate of                                          ˆ
                                                                 Y Forecast
     Negative change                                             Change
                                IV–Turning Point Error
                                Prediction or upturn
                                that did not occur; or failure
                                to predict a downturn
           of Negative change

Figure 2.6 Turning Point Error Diagram
                                  Model Evaluation
                                            Actual Change


Forecast Change


                  -300     -200      -100           0       100      200   300   400




                     Figure 2.7 Turning Point Analysis for Model C
              Chapter Summary

   Data Patterns

   Forecasting Methodologies

   Technique Selection

   Model Evaluation

To top