Predicting Demand from Sales Data in the Presence of Stockouts

Abstract

The effect of stockouts on prediction accuracy is analyzed. The forecasting bias that results and the effect on the prediction error variance are explored and are seen to depend on the frequency of stockouts, the coefficient of variation of demand, and the serial correlation of demand.

Retail Supply Chain Management

“…There is also opportunity to incorporate execution problems into models that estimate demand and assess forecast accuracy in the presence of stockouts (Wecker 1978;Raman and Zotteri 2000;. Raman and Zotteri, for example, argue that sales data could be used along with inventory data to incorporate lost sales estimates into the estimation of demand.…”

“…However, if the demand distribution is not known, which is often the case for a new product introduction, one has to rely on potentially censored data to estimate the unknown demand. Intuitively, if this partial observability of demand is not factored into the estimation procedure, the demand estimate will be biased low (Wecker 1978). If the low demand estimate is subsequently used to determine inventory stocking decisions, the resulting inventory level will also be biased low and thus will lead to more lost sales and an even lower future demand estimate.…”

“…The demand censoring problem is more prominent in brick-and-mortar stores than in online stores, because the latter can monitor and track customer purchases closely to alleviate such a problem. Academic researchers have long recognized the need to account for this censoring effect in demand forecasting and inventory management (e.g., Conrad 1976;Wecker 1978). This literature has been primarily centered on methodologies for dealing with the imperfect demand observations.…”

Demand estimation in lost sales inventory systems

“…Two studies that came to this writer's attention after preparing the original draft of this article are Wecker [20] and Conrad 141. Wecker considers the same problem we treat here but considers a more general type of demand process.…”

Predicting a Multitude of Time Series

“…Brown (1963) and Wecker (1978) discuss this approach in an inventory setting, and Whittle (1963. Sec.…”