Click-Conversion Multi-Task Model with Position Bias Mitigation for Sponsored Search in eCommerce
Authors:
- Yibo WangYWYibo Wang
- Yanbing XueYXYanbing Xue
- Bo LiuBLBo Liu
- Musen WenMWMusen Wen
- Wenting ZhaoWZWenting Zhao
- Stephen GuoSGStephen Guo
- Philip S. YuPYPhilip S. Yu
Preprint
Abstract
Position bias, the phenomenon whereby users tend to focus on higher-ranked items of the search result list regardless of the actual relevance to queries, is prevailing in many ranking systems. Position bias in training data biases the ranking model, leading to increasingly unfair item rankings, click-through-rate (CTR), and conversion rate (CVR) predictions. To jointly mitigate position bias in both item CTR and CVR prediction, we propose two position-bias-free CTR and CVR prediction models: Position-Aware Click-Conversion (PACC) and PACC via Position Embedding (PACC-PE). PACC is built upon probability decomposition and models position information as a probability. PACC-PE utilizes neural networks to model product-specific position information as embedding. Experiments on the E-commerce sponsored product search dataset show that our proposed models have better ranking effectiveness and can greatly alleviate position bias in both CTR and CVR prediction.Keywords
All Related Versions
- Version 1, 2023-07-29, ArXiv
- Published version: , 1884.
This publication has 4 references indexed in Scilit:
- Deep Multifaceted Transformers for Multi-objective Ranking in Large-Scale E-commerce Recommender Systems2020
- Unbiased Learning-to-Rank with Biased Feedback2017
- Evaluating the accuracy of implicit feedback from clicks and query reformulations in Web searchACM Transactions on Information Systems, 2007
- Accurately interpreting clickthrough data as implicit feedback2005