FORECASTING Kusdhianto Setiawan Gadjah Mada University
Steps of forecasting Determine objectives of forecasting Select the items or quantities that are to be forecasted Determine the time horizon Select the forecasting model/s Gather data Validate the model/s Make the forecast Implement the result
Type of forecasts Time series Causal models Qualitative models Delphi method Groups of experts in different locations make forecasts, involving 3 participants; decision making group, staff personnel, respondents Jury of Executive opinion; often involving high level managers, statistical models, estimate demand Sales force composite Consumer market Survey
Tools... Scatter Diagram...
Measures of Accuracy Forecast error (deviation) = actual value – forecast value Mean Absolute Deviation (MAD) MAD = ∑|forecast error|/n
Time Series Models Decomposition of a Time Series: Trend (T) Seasonality (S) Cycles (C) Random Variation (R) Models: Multiplicative; Demand=(TxSxCxR) Additive; Demand=(T+S+C+R)
Moving Averages Moving Average = ∑ demand in previous n periods/n Weighted MA = ∑(weight for period n)/(demand in period n) ∑ weights
Exponential Smoothing New Forecast = last period’s forecast + α (last period’s actual demand – last period’s forecast) F t = F t-1 + α (A t-1 – F t-1 )
Trend Projections Least Squares Method
Seasonal Variations See page 160 Tasks to prepare for the EXAM ! Continue reading the materials up to the end of this chapter ! Combine your knowledge on statistics, econometrics, and other subjects relevant to this study !