To find the average demand for a product, we could simply calculate the average of the historical observations. Since we are interested in averaged past data to project into the future, we could use an average of all the past demand data that were available for forecasting purposes. There are several reasons why this may not be desirable way of smoothing.
There may be so many periods of past data that storing them all is an issue. It is often true that the most recent history is of most relevance in forecasting the short-term demand in the near future. Recent data may reveal current conditions better than data that is several months or years old. For these reasons, many firms use the concept of a moving average for forecasting demand.
The Moving Average model as the name implies averages a selected number of past periods of data. The average moves because a new average can be calculated whenever a period’s demand is determined. Whenever a forecast is needed, the most recent past history of demand will be used to do the averaging.
The moving average forecast always uses the most recent period of historical information available for developing the forecast. The moving average is the forecast of demand for the next and subsequent periods.
