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.

翻译：基于Transformer的方法（如BERT4Rec和SASRec）在下一项推荐（NIR）任务中展现出强劲性能。然而，将这些架构应用于下一篮推荐（NBR）任务则面临挑战，因为篮中可能的物品组合数量巨大，且此类任务常涉及高度重复的交互。此外，基于频率的方法（如TIFU-KNN和UP-CF）在NBR任务中仍表现出强大性能，往往超越深度学习方法。本文提出SAFERec，一种用于NBR的新型算法，它通过融入物品频率信息来增强基于Transformer的NIR架构，从而提升其在NBR任务中的适用性。在多个数据集上的大量实验表明，SAFERec优于所有其他基线方法，特别是在Recall@10指标上实现了8%的提升。