Recurrent Convolution Basket Map for Diversity Next-Basket Recommendation

Leng, Youfang; Yu, Li; Xiong, Jie; Xu, Guanyu

doi:10.1007/978-3-030-59419-0_39

Cited by 10 publications

(2 citation statements)

References 19 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…various beyond-accuracy metrics. TREx must be considered or serve as a baseline before designing more sophisticated methods, such as including multi-objective loss functions [7,20], integer programming [53], and so on.…”

Section: Reflections and Discussionmentioning

confidence: 99%

“…Yu et al [50] argue that item-item relations between baskets are important, and leverage GNNs to use these relations. Some methods [3,20,39,42] exploit auxiliary information, including product categories, amounts, prices, and explicit timestamps. TIFUKNN [15] and UP-CF@r [12], frequency-neighbor-based methods, model temporal patterns, and then combine these with neighbor information or user-wise collaborative filtering.…”

Section: Related Workmentioning

confidence: 99%

See 1 more Smart Citation

A Next Basket Recommendation Reality Check

Jullien

Ariannezhad

et al. 2023

ACM Trans. Inf. Syst.

View full text Add to dashboard Cite

The goal of a next basket recommendation system is to recommend items for the next basket for a user, based on the sequence of their prior baskets. We examine whether the performance gains of the next basket recommendation (NBR) methods reported in the literature hold up under a fair and comprehensive comparison. To clarify the mixed picture that emerges from our comparison, we provide a novel angle on the evaluation of NBR methods, centered on the distinction between repetition and exploration: the next basket is typically composed of previously consumed items (i.e., repeat items) and new items (i.e., explore items). We propose a set of metrics that measure the repetition/exploration ratio and performance of NBR models. Using these new metrics, we provide a second analysis of state-of-the-art NBR models. The results help to clarify the extent of the actual progress achieved by existing NBR methods as well as the underlying reasons for any improvements that we observe. Overall, our work sheds light on the evaluation problem of NBR, provides a new evaluation protocol, and yields useful insights for the design of models for this task.

show abstract

Section: Reflections and Discussionmentioning

confidence: 99%