138 / 2024-04-21 23:01:24

Robust E-commerce Assortment and Operations Under the Multinomial Logit Choice Model

E-commerce,Assortment optimization,Customer choice,Robust optimization

The increasingly flourishing e-commerce has prompted online retailers to implement a two-layer distribution network consisting of regional and forward distribution centers. We study a joint assortment and operations planning problem that first selects and allocates the assortment before the horizon starts, then determines the inventory replenishment-allocation and demand fulfillment adaptively as random demands reveal over periods, which are endogenously generated by the assortment selection following a multinomial logit model. We formulate a multi-period stochastic optimization model to maximize the expected profit, which is transformed to a mixed-integer conic robust counterpart model. To further increase its tractability, we further propose a Benders branch-and-cut (BBC) algorithm, along with valid inequalities for tightening the upper bound and a two-phase heuristic for getting a good initial solution. Numerical results show that the BBC algorithm produces high-quality solutions within much short time for realistic-scale problems. A case study using real data from JD.com demonstrates the applicability of the BBC algorithm, which can potentially yield more profit over a status quo policy.