Rethinking Sequential Relationships: Improving Sequential Recommenders with Inter-Sequence Data Augmentation

Yang Jiao, Fan Yang, Yetian Chen, Yan Gao, Jia Liu, Yi Sun

Abstract: Predicting customer preferences for each item is a prerequisite module for most recommender systems in e-commerce. However, the sparsity of behavioral data is often a challenge to learn accurate prediction models. Given millions of items, each customer may only be able to interact with a small subset of them over time. This sparse behavioral data is insufficient to represent item-customer and item-item relations for a machine learning model to digest, resulting in limited prediction accuracy that hinders recommendation performance. To mitigate this issue, this study introduces an inter-sequence data augmentation method, SDAinter, that enhances data density by leveraging cross-customer behavioral patterns to enrich item relations. Tested on three public and one proprietary e-commerce dataset, SDAinter significantly increases data density, leading to notable improvements in both evaluation and business metrics. Our findings demonstrate SDAinter's effectiveness and its potential to complement existing data augmentation strategies in recommender systems. See https://github.com/ML-apollo/SDA_inter.