Use of Contextual and Model-Based Information in Behavioural Operations

Abstract

Despite the improvements in statistical forecasting, human judgment remains essential in business forecasting and demand planning. Typically, forecasters do not rely solely on statistical forecasts; they also adjust forecasts according to their knowledge, experience, and information that is not available to the statistical models. However, we have limited understanding of the adjustment mechanisms employed, particularly how people use additional information (e.g. special events and promotions, weather, holidays etc.) and under which conditions this is beneficial. Based on a UK-retailer case study, we first establish how event-driven software is used. We build on this by laboratory experiments that simulate a typical supply chain forecasting process. We provide past sales, statistical forecasts (simple baseline forecasts or statistical forecasts that include promotional effects) and qualitative information about past and future promotional periods. We find that when adjusting, forecasters tend to focus on model-based anchors, such as the last promotional uplift and the current statistical forecast, ignoring past baseline promotional values and additional information about previous promotions. The impact of contextual statements for the forecasting period depends on the type of statistical predictions provided: when statistical forecasts with promotional effects are presented, people tend to misinterpret the provided information and over-adjust, harming accuracy.