KDD2022

Promotheus: An End-to-End Machine Learning Framework for Optimizing Markdown in Online Fashion E-commerce

Eleanor Loh, Jalaj Khandelwal, Brian Regan, Duncan A. Little

5 citations

Abstract

Managing discount promotional events ("markdown") is a significant part of running an e-commerce business, and ineciencies here can signicantly hamper a retailer's protability. Traditional approaches for tackling this problem rely heavily on price elasticity modelling. However, the partial information nature of price elasticity modelling, together with the non-negotiable responsibility for protecting protability, mean that machine learning practitioners must often go through great lengths to dene strategies for measuring oine model quality. In the face of this, many retailers fall back on rule-based methods, thus forgoing signicant gains in profitability that can be captured by machine learning. In this paper, we introduce two novel end-to-end markdown management systems for optimising markdown at dierent stages of a retailer's journey. The rst system, "Ithax, " enacts a rational supply-side pricing strategy without demand estimation, and can be usefully deployed as a "cold start" solution to collect markdown data while maintaining revenue control. The second system, "Promotheus, " presents a full framework for markdown optimization with price elasticity. We describe in detail the specic modelling and validation procedures that, within our experience, have been crucial to building a system that performs robustly in the real world. Both markdown systems achieve superior protability compared to decisions made by our experienced operations teams in a controlled online test, with improvements of 86% (Promotheus) and 79% (Ithax) relative to manual strategies. These systems have been deployed to manage markdown at ASOS.com, and both systems can be fruitfully deployed for price optimization across a wide variety of retail e-commerce settings. CCS CONCEPTS • Applied computing ! Consumer products; Forecasting; Multi-criterion optimization and decision-making; Online auctions; • Mathematics of computing ! Statistical software.