Gespeichert in:
| Hauptverfasser: | , , , |
|---|---|
| Format: | Preprint |
| Veröffentlicht: |
2024
|
| Schlagworte: | |
| Online-Zugang: | https://arxiv.org/abs/2412.14302 |
| Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
| _version_ | 1866929641726410752 |
|---|---|
| author | Lashinin, Oleg Krasilnikov, Denis Milogradskii, Aleksandr Ananyeva, Marina |
| author_facet | Lashinin, Oleg Krasilnikov, Denis Milogradskii, Aleksandr Ananyeva, Marina |
| contents | 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. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2412_14302 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | SAFERec: Self-Attention and Frequency Enriched Model for Next Basket Recommendation Lashinin, Oleg Krasilnikov, Denis Milogradskii, Aleksandr Ananyeva, Marina Information Retrieval Artificial Intelligence 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. |
| title | SAFERec: Self-Attention and Frequency Enriched Model for Next Basket Recommendation |
| topic | Information Retrieval Artificial Intelligence |
| url | https://arxiv.org/abs/2412.14302 |