PI2I: A Personalized Item-Based Collaborative Filtering Retrieval Framework

TL;DR

PI2I is a two-stage personalized retrieval framework that improves item-based collaborative filtering by enhancing retrieval pool selection and modeling complex user-item interactions, leading to better recommendation performance.

Contribution

The paper introduces PI2I, a novel two-stage retrieval framework that significantly improves personalization in CF by optimizing retrieval and interaction modeling.

Findings

PI2I outperforms traditional CF methods in offline experiments.

PI2I rivals Two-Tower models in effectiveness.

Deployed in Taobao, PI2I increased online transaction rates by 1.05%.

Abstract

Efficiently selecting relevant content from vast candidate pools is a critical challenge in modern recommender systems. Traditional methods, such as item-to-item collaborative filtering (CF) and two-tower models, often fall short in capturing the complex user-item interactions due to uniform truncation strategies and overdue user-item crossing. To address these limitations, we propose Personalized Item-to-Item (PI2I), a novel two-stage retrieval framework that enhances the personalization capabilities of CF. In the first Indexer Building Stage (IBS), we optimize the retrieval pool by relaxing truncation thresholds to maximize Hit Rate, thereby temporarily retaining more items users might be interested in. In the second Personalized Retrieval Stage (PRS), we introduce an interactive scoring model to overcome the limitations of inner product calculations, allowing for richer modeling of intricate user-item interactions. Additionally, we construct negative samples based on the trigger-target (item-to-item) relationship, ensuring consistency between offline training and online inference. Offline experiments on large-scale real-world datasets demonstrate that PI2I outperforms traditional CF methods and rivals Two-Tower models. Deployed in the "Guess You Like" section on Taobao, PI2I achieved a 1.05% increase in online transaction rates. In addition, we have released a large-scale recommendation dataset collected from Taobao, containing 130 million real-world user interactions used in the experiments of this paper. The dataset is publicly available at https://huggingface.co/datasets/PI2I/PI2I, which could serve as a valuable benchmark for the research community.