EURO 2024 Copenhagen
Abstract Submission

EURO-Online login

3958. Large-scale dynamic assortment planning problem: a heuristic approach

Invited abstract in session TC-50: Assortment Management, stream Retail Operations.

Tuesday, 12:30-14:00
Room: M2 (building: 101)

Authors (first author is the speaker)

1. Mozart Menezes
Operations Management & Information Systems, NEOMA Business School -Bordeaux
2. Lijue Lu
Information System, Supply Chain Management & Decision Support Department, NEOMA Business School
3. Hamed Jalali
Department of information systems, supply chain management, and decision making, NEOMA Business school

Abstract

Single-period dynamic assortment planning refers to the retailer’s problem of deciding the set of products to offer and their initial inventory levels with stochastic demand and dynamic substitution. The goal of the retailer is to maximize its expected revenue subject to a capacity constraint on the total number of items offered. This problem is notoriously difficult to solve. We propose an efficient heuristic for this problem considering an online retailer that has hundreds of possible SKUs to choose from and has the possibility to stock thousand units in total. We impose no assumptions on preference lists and substitution patterns. Compared to the most recent heuristic, our algorithm is competitive in the average revenue obtained but it is significantly faster especially for large instances. We show that our approach performs well in a variety of settings.

Keywords

Status: accepted

Back to the list of papers