EURO-Online login
- New to EURO? Create an account
- I forgot my username and/or my password.
- Help with cookies
(important for IE8 users)
3405. Order Allocation Optimization in a Fashion Marketplace
Invited abstract in session WA-50: Retail Distribution I, stream Retail Operations.
Wednesday, 8:30-10:00Room: M2 (building: 101)
Authors (first author is the speaker)
| 1. | Sérgio Castro
|
| INESC TEC | |
| 2. | Gonçalo Figueira
|
| INESC-TEC, Faculty of Engineering of Porto University | |
| 3. | Bernardo Almada-Lobo
|
| INESC-TEC, Faculty of Engineering of Porto University |
Abstract
Order allocation is the dynamic problem of distributing incoming orders to fulfillment nodes. This problem appears in different sectors and contexts, where the nodes may belong to the same or independent vendors. We consider an Online Fashion Marketplace selling products owned by multiple vendors. In this setting, customers expect immediate feedback on their product fulfillment, such that order allocation decisions must be taken instantly.
This particular Marketplace diverges significantly from prior studies in order allocation literature due to the consistent low sales volume per item across the majority of the product portfolio, and the daily fluctuations in inventory by vendors that introduce a notable level of uncertainty.
Given the distinctive characteristics of this problem compared to existing literature, we propose an innovative methodology to generate heuristic fulfillment policies. Leveraging either Genetic Programming or Genetic Algorithms, we incorporate critical policy information, including shipping costs, basket coverage and stock depth into a machine learning pipeline to generate policies that are fast and effective.
To assess the efficacy of the proposed policies, a comprehensive comparative analysis is conducted against the retailer's existing policy and a perfect hindsight policy, from which managerial insights are extracted.
Keywords
- E-Commerce
- Logistics
Status: accepted
Back to the list of papers