91Ó°ÊÓ

Exponential smoothing is an appropriate forecasting technique if the time series exhibits a horizontal pattern (i.e. No trend) with random fluctuations. However, if the time series exhibits a trend, forecasts supported by 1 simple exponential smoothing will lag the trend. In such cases, a variation of easy exponential smoothing called the trend-adjusted exponential smoothing may be used as a forecasting technique.

If by using exponential smoothing with an adjustment for trend, demand is increasing at a very steady rate of about five units per week, alpha and delta parameters to be zero,because exponential smoothing is an appropriate forecasting technique, if the time series exhibits a horizontal pattern (i.e. No trend) with random fluctuations.

However, if the time series exhibits a trend, forecasts supported by simple exponential smoothing will lag the trend. In such cases, a variation of easy exponential smoothing called the trend-adjusted exponential smoothing may be used as a forecasting technique. "The trend-adjusted forecast (Taf) has two components: A smoothed error A trend factor Taft = St-1 + Tt-1,

Where St-1 = Previous period smoothed forecast

Tt-1 = Previous period trend estimate

Taft = Current period's trend-adjusted forecast

St = Taft + alpha (At – Taft)

Tt = Tt-1 + beta(Taft - Taft-1 - Tt-1), where alpha and beta are smoothing constants To use this method, one must select values of alpha and beta (usually through trial and error) and make a starting forecast and an estimate of the trend.