Unified Learning-to-Rank for Multi-Channel Retrieval in Large-Scale E-Commerce Search

TL;DR

This paper introduces a unified learning-to-rank model for multi-channel e-commerce search that optimizes document merging based on query-specific utility, improving conversion rates while maintaining strict latency constraints.

Contribution

It proposes a novel query-dependent learning-to-rank approach that jointly optimizes multiple business KPIs and incorporates user behavioral signals for multi-channel retrieval.

Findings

Achieved +2.85% improvement in user conversion in online experiments.

Outperformed traditional rank-based fusion methods.

Maintained production latency with p95 latency under 50 ms.

Abstract

Large-scale e-commerce search must surface a broad set of items from a vast catalog, ranging from bestselling products to new, trending, or seasonal items. Modern systems therefore rely on multiple specialized retrieval channels to surface products, each designed to satisfy a specific objective. A key challenge is how to effectively merge documents from these heterogeneous channels into a single ranked list under strict latency constraints while optimizing for business KPIs such as user conversion. Rank-based fusion methods such as Reciprocal Rank Fusion (RRF) and Weighted Interleaving rely on fixed global channel weights and treat channels independently, failing to account for query-specific channel utility and cross-channel interactions. We observe that multi-channel fusion can be reformulated as a query-dependent learning-to-rank problem over heterogeneous candidate sources. In this paper, we propose a unified ranking model that learns to merge and rank documents from multiple retrieval channels. We formulate the problem as a channel-aware learning-to-rank task that jointly optimizes clicks, add-to-carts, and purchases while incorporating channel-specific objectives. We further incorporate recent user behavioral signals to capture short-term intent shifts that are critical for improving conversion in multi-channel ranking. Our online A/B experiments show that the proposed approach outperforms rank-based fusion methods, leading to a +2.85\% improvement in user conversion. The model satisfies production latency requirements, achieving a p95 latency of under 50\,ms, and is deployed on Target.com.