Estimation of Consumer Demand with Stock--out Based Substitution: An Application to Vending Machine Products

R. Anupindi, M. Dada and S. Gupta

*** Abstract ****

In this paper we develop a model of customer arrivals and choice between goods that allows for possible product substitution and lost sales when a customer faces a stock-out at retail. The model is formulated in the context of retail vending, an industry that accounts for a sizable part of the retail sales of many consumer products. We focus on the problem of estimating core demand rates and substitution rates between items in the assortment carried, based on information available from two different kinds of inventory tracking systems. In the best case scenario of a perpetual inventory system in which times of stock-out occurrence and cumulative sales of all goods at these times are observed, we derive Maximum Likelihood Estimates (MLEs) of the demand parameters and show that they are especially simple and intuitive. However, state-of-the-art inventory systems in retail vending provide only periodic data, i.e., data in which times of stock-out occurrence are unobserved or ``missing''. For these data we show how the Expectation-Maximization (E-M) algorithm may be employed to obtain the MLEs by treating the stock-out times as missing data. The model is applied to daily sales and stock data from beverage vending machines in a mid-Western US city.