2.2.The Time Horizon in Forecasting Short-term sales Product family sales Shift schedule Labor needs Resource requirements Resource requirements Days/Weeks Intermeo Weeks/Months Short Long Capacity needs Long-term sales patterns Growth trends Fig.2-1 Forecast Horizons in Operation Planning
Fig.2-1 Forecast Horizons in Operation Planning 2.2. The Time Horizon in Forecasting
图 2.3.Classification of Forecasts .Sales force composites; Subjective-based .Customer surveys; on human Jury of executive opinion; judgment .The Delphi method. .Causal Models Objective-derived from analysis of data .Time Series Methods
Subjective-based on human judgment Objective-derived from analysis of data •Sales force composites; •Customer surveys; •Jury of executive opinion; •The Delphi method. •Causal Models •Time Series Methods 2.3. Classification of Forecasts
2.4.Evaluating Forecast The forecast error e,in period t is the difference between the forecast value for that period and the actual demand for that period. e,=F-D The three measures for evaluating forecasting accuracy during n period MD=∑Ie,l MsE=∑e MAPE=[∑1e,/D,IxI00 n i=l n i=1 n i=l MAD:The mean absolute deviation,preferred method; MSE:The mean squared error; MAPE:The mean absolute percentage error(MAPE)
The forecast error et in period t is the difference between the forecast value for that period and the actual demand for that period. ttt e FD The three measures for evaluating forecasting accuracy during n period 2 1 1 n i i MSE e n • MAD: The mean absolute deviation, preferred method; • MSE: The mean squared error; • MAPE: The mean absolute percentage error (MAPE) 1 1 | | n i i MAD e n 1 1[ | / |] 100 n i i i MAPE e D n 2.4. Evaluating Forecast
2.6.Methods of Forecasting Stationary Series Stationary time series:each observation can be represented by a constant plus a random fluctuation. D,=u+8 where u an unknown constant corresponding to mean of the series; the random error with mean zero and variation o2. ·Methods: √Moving average, Exponential Smoothing
Stationary time series: each observation can be represented by a constant plus a random fluctuation. Dt t where = an unknown constant corresponding to mean of the series; = the random error with mean zero and variation 2. • Methods: Moving average; Exponential Smoothing 2.6. Methods of Forecasting Stationary Series
2.6.Methods of Forecasting Stationary Series Moving Average -A moving average of order N is simply the arithmetic average of the most recent N observations (one- step-ahead),denoted as MA(N). E=20=D+D++D小 F D N past data t-N 23 t-1 t
Moving Average -A moving average of order N is simply the arithmetic average of the most recent N observations (onestep-ahead), denoted as MA(N). 1 2 1 1 1 ( ) N t ti t t tN i F D DD D N N 1 2 3 t-1 t D1 D2 Dt-N Dt-1 Ft Dt-2 … … N past data 2.6. Methods of Forecasting Stationary Series