BU385 Lecture Notes - Lecture 11: Time Series, Exponential Smoothing, Moving Average
Document Summary
Estimate of expected demand during a specific future period. Technique that averages a number of recent actual values as forecast for current period. Calculate a three-period moving average forecast for the demand for a product, given its demand for the last five periods: F6 = 43 + 40 + 41 = 41. 33. A variation of moving average where most recent values in the time series are given larger weight in calculating a forecast. F6 = 0. 1(40) + 0. 2(43) + 0. 3(40) + 0. 4(41) = 41. 0. Advantage of a weighted moving average over a simple moving average is that the weighted moving average is more reflective of the most recent observations. Weighted averaging method based on previous forecast plus a percentage of the different between that forecast and the previous actual value. Forecast = previous forecast + a(previous actual previous forecast) Suppose that the previous forecast was 42 units, previous actual demand was 40 units and a = 0. 1.
