Moving Average The moving average method is conceptually quite simple. Consider the forecast that next year’s sales will be equal to this year’s sales. Such a forecast might be subject to large error if these is much fluctuation in sales from one year to the next. To allow for such randomness, we might consider using some kind of average of recent value. For example, we might average the last two years’ sales, the last three years’ sales, the last five years’ sales, or any number of ther periods. The forecast would simply be the average that resulted. The number of observation included in the average is typically determined by trial and error. Differing numbers of periods are tried, and the number of periods that produce the most accurate forecasts of the trial data is used to develop the forecast model. Once determined, it remains constant. The term moving average is used because a new message is computed and used as a forecast as each new observation becomes available.