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

Fuente: arXiv
Gespeichert in:
Bibliographische Detailangaben
Hauptverfasser: Zeng, Xiangyu, Jaspal, Amit, Liu, Bin, Panneeru, Goutham, Huang, Kevin, Bievre, Nicolas, Jaggi, Mohit, Maniraju, Prathap, Jain, Ankur
Format: Preprint
Veröffentlicht: 2025
Schlagworte:
Online-Zugang:
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
_version_ 1866915401405825024
author Zeng, Xiangyu
Jaspal, Amit
Liu, Bin
Panneeru, Goutham
Huang, Kevin
Bievre, Nicolas
Jaggi, Mohit
Maniraju, Prathap
Jain, Ankur
author_facet Zeng, Xiangyu
Jaspal, Amit
Liu, Bin
Panneeru, Goutham
Huang, Kevin
Bievre, Nicolas
Jaggi, Mohit
Maniraju, Prathap
Jain, Ankur
contents 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.
format Preprint
id arxiv_https___arxiv_org_abs_2507_15113
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Click A, Buy B: Rethinking Conversion Attribution in E- Commerce Recommendations
Zeng, Xiangyu
Jaspal, Amit
Liu, Bin
Panneeru, Goutham
Huang, Kevin
Bievre, Nicolas
Jaggi, Mohit
Maniraju, Prathap
Jain, Ankur
Information Retrieval
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.
title Click A, Buy B: Rethinking Conversion Attribution in E- Commerce Recommendations
topic Information Retrieval
url https://arxiv.org/abs/2507.15113