Demand Forecasts

1
Demand Forecasts

• The three principles of all forecasting
  techniques
• Forecasting is always wrong
• Every forecast should include an estimate of
  error
• The longer the forecast horizon the worst is the
  forecast
• Aggregate forecasts are more accurate

2
Two comments frequently made by managers

• Weve got to have better forecasts
• I dont trust these forecasts or understand where
  they came from
• These comments suggest that forecasts are held in
  disrepute by many managers

3
The truth about forecasts

• They are always wrong
• Sophisticated forecasting techniques do not mean
  better forecasts
• Forecasting is still an art rather than an
  esoteric science
• Avoid single number forecasting
• Single number substitutes for the decision

4
Selecting a forecasting technique

• What is the purpose of the forecast?
• How is it to be used?
• What are the dynamics of the system for which
  forecast will be made?
• How important is the past in estimating the
  forecast?

5
Forecasting Techniques

• Judgmental methods
• Market research methods
• Time series methods
• Casual methods

Qualitative
Quantitative
6
Judgmental methods

• Sales-force composite
• Panels of experts
• Delphi method

7
Market research method

• Markey testing
• Market survey

8
Time Series methods

• Moving average
• Exponential smoothing
• Trend analysis
• Seasonality
• Use de-seasonalized data for forecast
• Forecast de-seasonalized demand
• Develop seasonal forecast by applying seasonal
  index to base forecast

9
Components of an observation

• Observed demand (O)
• Systematic component (S) Random component (R)

Level (current deseasonalized demand)
Trend (growth or decline in demand)
Seasonality (predictable seasonal fluctuation)
10
Causal methods

• Single Regression analysis
• Multiple Regression analysis

11
Error measures

• MAD
• Mean Squared Error (MSE)
• Mean Absolute Percentage Error (MAPE)
• Bias
• Tracking Signal

12
Collection and preparation of data

• Record data in the same terms as needed for
  forecast
• Demand vs. shipment
• Time interval should be the same
• Record circumstances related to data
• Record demand separately for different customer
  groups

13
Time Series Forecasting
Forecast demand for the next four quarters.
14
Time Series Forecasting