SAFERec: Self-Attention and Frequency Enriched Model for Next Basket Recommendation
This work addresses a domain-specific problem in recommendation systems for users, but it is incremental as it builds on existing transformer and frequency-based methods.
The paper tackled the challenge of applying transformer-based models to Next-Basket Recommendation tasks, which involve repetitive interactions and many item combinations, by introducing SAFERec, a model that incorporates item frequency information, resulting in an 8% improvement in Recall@10 over baselines.
Transformer-based approaches such as BERT4Rec and SASRec demonstrate strong performance in Next Item Recommendation (NIR) tasks. However, applying these architectures to Next-Basket Recommendation (NBR) tasks, which often involve highly repetitive interactions, is challenging due to the vast number of possible item combinations in a basket. Moreover, frequency-based methods such as TIFU-KNN and UP-CF still demonstrate strong performance in NBR tasks, frequently outperforming deep-learning approaches. This paper introduces SAFERec, a novel algorithm for NBR that enhances transformer-based architectures from NIR by incorporating item frequency information, consequently improving their applicability to NBR tasks. Extensive experiments on multiple datasets show that SAFERec outperforms all other baselines, specifically achieving an 8\% improvement in Recall@10.