Optimizing product assortment under customer-driven demand substitution
Introduction
In order to survive in a competitive environment and to establish a strong position in the market, retailers should be able to manage their operational activities efficiently while providing an adequate customer service-level. Activities such as store and inventory management, establishing relationships with the suppliers, ordering and purchasing of products all contribute to operational costs, while additional costs, or rather loss of revenue, may incur due to poor quality procurement and customer dissatisfaction. An important trade-off in finding the right product assortment is that increasing variety increases customer satisfaction but has a negative effect on operational costs. As a result, when a retailer decides on which suppliers to work with and what product assortment to carry, it is important to understand the expectations and the purchasing behaviors of customers. Research on this topic shows that customers are frequently willing to buy a different color, size or brand within a product category if their favorite variant is either not offered or is temporarily out of stock, rather than going home empty handed. This behavior is indicated by the term customer-driven demand substitution and causes the demand for the remaining product types to increase, affecting their optimal order quantities and the product assortment decisions. In selecting what products to offer, retailers are subject to store related constraints such as shelf and storage space limitations. Therefore, maximizing profit in the existence of these operational issues is a challenging problem for retailers as they seek to rationalize assortment and inventory decisions at the category level.
Product assortment, demand substitution, supplier selection, and inventory management have been studied extensively; yet, to the best of our knowledge, there is no previous work that considers all these aspects together in the literature. This paper provides a tool for retailers to determine the product assortment, which considers supplier selection and inventory management decisions in the presence of shelf space limitations and substitution behavior of customers. The proposed tool optimizes these inter-related decisions for each product category with the goal of maximizing the retailer’s expected profits, under cost and demand parameters to be estimated by the retailer over a time horizon. Specifically, we introduce a mixed-integer programming model for the joint problem in order to determine which product types should be ordered from the suppliers, as well as the optimal ordering quantities for the offered product types. The model finds an optimal policy that maximizes expected total profit over a planning horizon for which demand and customers’ substitution preferences can be forecasted. By solving this model with different parameter settings designed in our computational experiments, we analyze the importance of various aspects of the problem. We identify the effect of substitution on the product assortment and profit by varying substitution cost parameters. In addition, we show numerically that incorporating the supplier selection decision into the determination of product assortment may result in significantly increased profit, and furthermore, considering shelf space limitations in the decision process leads to more profitable assortments.
The rest of the paper is organized as follows. Section 2 provides the necessary background and literature on product assortment, demand substitution, and supplier selection problems. The mathematical model for the problem with single-period, stochastic demand is presented in Section 3. An illustrative example is also presented in this section. In Section 4, the model is analyzed computationally. Conclusions are drawn in Section 5, where possible extensions to the proposed model are also discussed.
Section snippets
Literature review
Our focus in this paper is on product assortment under demand substitution, together with other relevant retail store management issues such as shelf space allocation and supplier selection decisions. In this section, we first review previous work on inventory management in the existence of both product assortment and demand substitution, specifically in the retailing context, and then mention some related papers from the supplier selection literature.
Several researchers considered demand
Problem setting: definitions and assumptions
We consider two types of important decisions that must be made by a retailer. On the tactical level, the retailer must choose which products to offer to its customers and which suppliers to work with. On the operational level, given the assortment and the suppliers, the retailer must choose how much to order from each product taking into consideration consumers’ reaction to the assortment and the inventory availability. Traditionally, these two problems have been treated separately. Relatively
Experimental analysis
In our computational experiments we generated instances with 10 products (with the 11th product representing lost sales), and 5 suppliers. We assume that customers perform at most 3 levels of substitution . This is a reasonable value for the maximum substitution level since substitution rates tend to become very small at higher levels. Moreover, we assume the substitution cost is a linear function of the substitution level, m. That is, we let , where denotes the first level
Conclusion
The problem of product assortment under customer-driven demand substitution in retail operations is analyzed in this paper. We developed a model for the multi-product inventory, product assortment and supplier selection problem with multi-level demand substitution. The behavior of the solution provided by the model is analyzed for the single-period problem with stochastic demand. The analysis is performed to examine the effects of three parameters, substitution cost, supplier selection cost,
Acknowledgement
Financial support from KUMPEM-Koç University Migros Retail Education Center is gratefully acknowledged.
References (29)
- et al.
The impact of product substitution on retail merchandising
European Journal of Operational Research
(2001) - et al.
Inventory control under substitutable demand: A stochastic game application
Naval Research Logistics
(2002) - et al.
Improving purchasing productivity at IBM with a normative decision support system
Interfaces
(1985) - E. Bish, B. Maddah, On the interaction between variety, pricing, and inventory decisions under consumer choice, Working...
- et al.
GAMS: A User’s Guide
(1998) - et al.
A goal programming model for purchase planning
Journal of Purchasing and Materials Management
(1983) - et al.
Retail assortment planning in the presence of consumer search
Manufacturing and Service Operations Management
(2005) - et al.
An evaluation of vendor selection models from a total cost of ownership perspective
European Journal of Operational Research
(2000) - et al.
Impact of deals and deal retraction on brand switching
Journal of Marketing Research
(1978) - M. Fadilog¯lu, O. Karaşan, M. Pinar, A model and case study for efficient shelf usage and assortment analysis, Working...
Assortment planning and inventory decisions under a locational choice model
Management Science
A logit model of brand choice calibrated on scanner panel data
Marketing Science
Random yield and random demand in a production system with downward substitution
Operations Research
Cited by (80)
Multi-plant manufacturing assortment planning in the presence of transshipments
2023, European Journal of Operational ResearchThe intermediating role of big data analytics capability between responsive and proactive market orientations and firm performance in the retail industry
2023, Journal of Retailing and Consumer ServicesProduct line optimization with multiples sites
2022, Computers and Operations ResearchCapacitated assortment planning of a multi-location system under transshipments
2022, International Journal of Production EconomicsJoint assortment and inventory optimization for vertically differentiated products under consumer-driven substitution
2022, European Journal of Operational ResearchCitation Excerpt :Other studies assume a single attempt substitution with a higher substitution rate to approximate the problem with multiple substitution attempts (e.g., Kök, 2003). Yücel, Karaesmen, Salman, & Türkay (2011) consider deterministic demand and deterministic substitution behavior and develop a mixed-integer program. Besides the restricted deterministic setting, the authors take some more practical issues into account, such as shelf space restrictions, ordering quotas, and supplier selection.
Inventory management for the in-flight catering industry: A case of uncertain demand and product substitutability
2022, Computers and Industrial Engineering