Segment Discovery: Enhancing E-commerce Targeting

2024-09-20

arXiv.org

AI Summary

In e-commerce marketing, conventional intervention targeting suffers from low efficiency in identifying high-impact users and struggles to jointly satisfy operational constraints (e.g., budget, coverage) and maximize incremental value. Method: This paper proposes a precise intervention framework that integrates uplift modeling with explicit constraint optimization. It is the first to jointly formulate causal uplift models (e.g., X-Learner) and mixed-integer programming (MIP) to enable value-driven, fine-grained user segmentation under hard constraints—including budget limits and regulatory compliance—moving beyond coarse-grained, response-rate–based targeting. Contribution/Results: The framework ensures interpretability and production readiness. Evaluated on a live A/B test involving millions of users and deployed in a top-tier e-commerce platform’s production system, it achieves an 18.7% improvement in incremental conversion value over state-of-the-art methods while strictly adhering to budgetary and compliance requirements. It has been scaled to full production deployment.

Technology Category

• Search and Optimization: Mixed Discrete/Continuous Search
• Constraint Satisfaction and Optimization: Distributed CSP/Optimization
• Machine Learning: Causal Learning

Application Category

• User Modeling, Personalization and Recommendation: User modeling for targeted and personalized online advertising
• Economics, Online Markets and Human Computation: Incentives in network design for Web infrastructures and ecosystems
• Responsible Web: Human-perceived consequences of algorithmic deployment on the web

Abstract

Modern e-commerce services frequently target customers with incentives or interventions to engage them in their products such as games, shopping, video streaming, etc. This customer engagement increases acquisition of more customers and retention of existing ones, leading to more business for the company while improving customer experience. Often, customers are either randomly targeted or targeted based on the propensity of desirable behavior. However, such policies can be suboptimal as they do not target the set of customers who would benefit the most from the intervention and they may also not take account of any constraints. In this paper, we propose a policy framework based on uplift modeling and constrained optimization that identifies customers to target for a use-case specific intervention so as to maximize the value to the business, while taking account of any given constraints. We demonstrate improvement over state-of-the-art targeting approaches using two large-scale experimental studies and a production implementation.

Problem

• Online Shopping Service
• Precision Improvement
• Resource Optimization

Innovation

• Advanced Mathematical Tools
• Targeted Online Shoppers
• Enhanced Commercial Effectiveness