Name
Abstract | ||
|---|---|---|
We developed a novel multiobjective markdown system and deployed it across many merchandising units at Walmart. The objectives of this system are to (1) clear the stores' excess inventory by a specified date, (2) improve revenue by minimizing the discounts needed to clear shelves, and (3) reduce the substantial cost to relabel merchandise in the stores. The underlying mathematical approach uses techniques such as deep reinforcement learning, simulation, and optimization to determine the optimal (markeddown) price. Starting in 2019, after six months of extensive testing, we implemented the new approach across all Walmart stores in the United States. The result was a high-performance model with a price-adjustment policy tailored to each store. Walmart increased its sell-through rate (i.e., the number of units sold during the markdown period divided by its inventory at the beginning of the markdown) by 21% and reduced its costs by 7%. Benefits that Walmart accrues include demographics-based store personalization, reductions in operating costs with limited numbers of price adjustments, and a dynamic time window for markdowns. |
Year | DOI | Venue |
|---|---|---|
2021 | 10.1287/inte.2020.1065 | INFORMS JOURNAL ON APPLIED ANALYTICS |
Keywords | DocType | Volume |
merchandising, price optimization, inventory optimization, deep reinforcement learning, Edelman Award | Journal | 51 |
Issue | ISSN | Citations |
1 | 2644-0865 | 0 |
PageRank | References | Authors |
0.34 | 0 | 9 |
Name | Order | Citations | PageRank |
|---|---|---|---|
| Yixian Chen | 1 | 0 | 0.34 |
| Prakhar Mehrotra | 2 | 0 | 0.34 |
| Nitin Kishore Sai Samala | 3 | 0 | 0.34 |
| Kamilia Ahmadi | 4 | 0 | 0.34 |
| Viresh Jivane | 5 | 0 | 0.34 |
| Linsey Pang | 6 | 1 | 1.11 |
| Monika Shrivastav | 7 | 0 | 0.34 |
| Nate Lyman | 8 | 0 | 0.34 |
| Scott Pleiman | 9 | 0 | 0.34 |