Click A, Buy B: Rethinking Conversion Attribution in E- Commerce Recommendations

TL;DR

This paper addresses the challenge of accurately attributing conversions in e-commerce by distinguishing genuine product substitutions from coincidental cross-category purchases, improving recommendation models and business metrics.

Contribution

It introduces a multi-task learning framework with a taxonomy-aware weighting scheme to better identify true conversion signals in e-commerce data.

Findings

Offline evaluation reduced normalized entropy by 13.9%.

Online A/B test achieved +0.25% improvement in key metric.

Proposed method better isolates genuine conversion signals.

Abstract

User journeys in e-commerce routinely violate the one-to-one assumption that a clicked item on an advertising platform is the same item later purchased on the merchant's website/app. For a significant number of converting sessions on our platform, users click product A but buy product B -- the Click A, Buy B (CABB) phenomenon. Training recommendation models on raw click-conversion pairs therefore rewards items that merely correlate with purchases, leading to biased learning and sub-optimal conversion rates. We reframe conversion prediction as a multi-task problem with separate heads for Click A Buy A (CABA) and Click A Buy B (CABB). To isolate informative CABB conversions from unrelated CABB conversions, we introduce a taxonomy-aware collaborative filtering weighting scheme where each product is first mapped to a leaf node in a product taxonomy, and a category-to-category similarity matrix is learned from large-scale co-engagement logs. This weighting amplifies pairs that reflect genuine substitutable or complementary relations while down-weighting coincidental cross-category purchases. Offline evaluation on e-commerce sessions reduces normalized entropy by 13.9% versus a last-click attribution baseline. An online A/B test on live traffic shows +0.25% gains in the primary business metric.