مدیریت موجودی خرده فروشی با جایگزینی تقاضای پویای سهام

We consider an inventory management problem of a product category in a retail setting with Poisson arrival processes, stock-out based dynamic demand substitution, and lost sales. The retailer uses a fixed-review period, order-up-to level system to control the inventory levels. We present a computational method to determine the order-up-to levels that maximizes the expected profit with profit margins, inventory holding and substitution costs subject to service-level constraints. Determining expected sales, average inventory levels, and number of substitutions between all products for given demand rates, substitution probabilities, and order-up-to levels is not tractable when there are more than two products. Therefore we present efficient and accurate approximations to approximately compute the same performance measures. The approximate approaches are then used to solve the optimization problem by using a genetic algorithm. In a computational study, we discuss the impact of profit margins, inventory holding and substitution costs, and service level constraints on the order-up-to levels and the expected profits. We show that a retailer can increase its expected profits by incorporating substitution among different products.

This paper studies an inventory management problem in a retail setting with stock-out based substitutions and multiple items in a product category and proposes an approximate solution to determine the order-up-to levels to maximize the expected profit subject to service level constraints. The method uses demand parameters including the substitution probabilities estimated from the point-of-sales data. As a result, the method provides a practical tool for retailers to manage their inventory. The literature on inventory management under stock-out based substitutions studies the supplier-(or manufacturer-)controlled and customer-driven substitution schemes. In the supplier-controlled substitution scheme, in a stock-out instance, the supplier decides whether to fulfill the demand of the customer with another product. The inventory management (and/or production planning) problem is usually studied in a “one-way substitution” setting, where a higher-graded product can be substituted for a lower-graded product. The primary objective is to minimize the sum of production, inventory holding, and, in some cases, product conversions costs. A detailed discussion of the relevant literature on supplier-controlled substitution is presented in Hsu et al. (2005) and Rao et al. (2004). In this paper, inventory management under the customer-driven substitution scheme is studied. In the customer-driven substitution scheme, when the first-choice product of the customer is not available on the shelf, the customer may purchase, with a certain probability, another product in the same category in lieu of her first-choice product. Although the retailer can only indirectly affect customers' decisions through his inventory management decisions, ignoring product substitutions in managing the inventories may result in sub-optimal performance: Mahajan and van Ryzin (2001) analyze a single-period, stochastic inventory problem with substitutable products, and show that “substitution effects can have a significant impact on an assortment's gross profits.” Ernst and Kamrad (2006) study a two-product problem with customer-driven substitution in a newsvendor setting, and conclude that “using a Newsboy Model framework without regard to substitutions can be sub-optimal.” In the single-period models, it

In this paper, we consider the inventory management problem of a product category with stock-out based dynamic demand substitutions and lost sales. Although the retailer can only indirectly affect customers' decisions through his inventory management decisions, as discussed in the literature, ignoring product substitutions in managing the inventories may result in sub-optimal performance. We present an approximate approach to find the order-up-to levels in a profit maximization setting with profit margins, inventory holding and substitution costs, and service level constraints. Through a computational study, we show that, by explicitly accounting for substitutions, the performance of the inventory system can be improved. The amount of improvement depends on the minimum direct service level requirement as well as the correlation between the market share and the profit margin of the products. By combining the method we presented in an earlier study to estimate the demand and customer choice parameters, the method we presented in this study can be used to manage inventory in a better way in retailing.