Providing support for the use of analogies in demand forecasting tasks

Management judgment is widely used to adjust statistical forecasts in order to take into account special events, such as sales promotions. There is evidence that forecasters often use information from analogous events from the past to help to estimate the effects of an anticipated special event. Unaided forecasters using such an approach may suffer from errors in recall, difficulties in making judgments about similarity, and difficulties in adapting the information from analogous events to match the attributes of the anticipated event. We conducted an experiment to investigate whether a forecasting support system (FSS), which provided users with guidance on similarity judgments and support for adaptation judgments, could lead to more accurate forecasts of the effects of sales promotions. The experiment suggested that a simple, easily implemented form of adaptation support could significantly improve forecast accuracy under some conditions. The support is also likely to be acceptable to potential users.