55 Pages Posted: 17 Oct 2016 Last revised: 11 Nov 2016
Date Written: October 16, 2016
This work is motivated by a new checkout recommendation system at Walmart's online grocery, which offers a customer an assortment of up to 8 items that can be added to an existing order, at potentially discounted prices. We formalize this as an online assortment planning problem under limited inventory, with customer types defined by the items initially selected in the order. Multiple item prices, combined with customer withdrawal when their initially selected items stock out, pose additional challenges for the development of an online policy. We overcome these challenges by introducing the notion of an inventory protection level in expectation, and presenting an algorithm with bounded competitive ratio when the arrival sequence is chosen adversarially. We further conduct numerical experiments which compare the performance of our algorithm with several existing benchmarks.
Keywords: revenue management, personalized recommendation, assortment planning, online algorithms, competitive ratio, protection level
Suggested Citation: Suggested Citation
Chen, Xi and Ma, Will and Simchi-Levi, David and Xin, Linwei, Dynamic Recommendation at Checkout under Inventory Constraint (October 16, 2016). Available at SSRN: https://ssrn.com/abstract=2853093 or http://dx.doi.org/10.2139/ssrn.2853093