Interactive Sequential Basket Recommendation by Learning Basket Couplings and Positive/Negative Feedback
Wei Wang and Longbing Cao. access the paper, ACM Transactions on Information Systems, 39(3): 1-26, 2021.

Sequential recommendation such as next-basket recommender systems (NBRS) which models users’ sequential behaviors and the relevant context/session has recently attracted much attention from the research community. Existing session-based NBRS involve session representation and inter-basket relations but ignore their hybrid couplings with the intra-basket items, often producing irrelevant or similar items in the next basket. In addition, they do not predict next-baskets (more than one next basket recommended). Interactive recommendation further involves user feedback on the recommended basket. The existing work on next-item recommendation involves positive feedback on selected items but ignores negative feedback on unselected ones. Here, we introduce a new setting – interactive sequential basket recommendation, which iteratively predicts next baskets by learning the intra-/inter-basket couplings between items and both positive/negative user feedback on recommended baskets. A hierarchical attentive encoder-decoder model (HAEM) continuously recommends next baskets one after another during sequential interactions with users after analyzing the item relations both within a basket and between adjacent sequential baskets (i.e., intra-/inter-basket couplings) and incorporating the user selection and unselection (i.e., positive/negative) feedback on the recommended baskets to refine NBRS. HAEM comprises a basket encoder and a sequence decoder to model intra-/inter-basket couplings and a prediction decoder to sequentially predict next-baskets by interactive feedback-based refinement. Empirical analysis shows that HAEM significantly outperforms the state-of-the-art baselines for NBRS and session-based recommenders for accurate and novel recommendation. We also show the effect of continuously refining sequential basket recommendation by including unselection feedback during interactive recommendation.

 
VM-NSP: Vertical Negative Sequential Pattern Mining with Loose Negative Element Constraints
Wei Wang and Longbing Cao. access the paper, ACM Transactions on Information Systems, 39(2): 1-27, 2021.

Negative sequential patterns (NSPs) capture more informative and actionable knowledge than classic positive sequential patterns (PSPs) due to the involvement of both occurring and nonoccurring behaviors and events, which can contribute to many relevant applications. However, NSP mining is non-trivial as it involves fundamental challenges requiring distinct theoretical foundations and is not directly addressable by PSP mining. In the very limited research reported on NSP mining, a negative element constraint (NEC) is incorporated to only consider the NSPs composed of specific forms of elements (containing either positive or negative items), which results in many valuable NSPs being missed. Here, we loosen the NEC (called loose NEC, i.e., LNEC) to include partial negative elements containing both positive and negative items, which enables the discovery of more flexible patterns but incorporates significant new learning challenges, such as representing and mining complete NSPs. Accordingly, we formalize the LNEC-based NSP mining problem and propose a novel vertical NSP mining framework, VM-NSP, to efficiently mine the complete set of NSPs by a vertical representation of each sequence. An efficient bitmap-based vertical NSP mining algorithm, bM-NSP, introduces a bitmap hash table-based vertical representation and a prefix-based negative sequential candidate generation strategy to optimize the discovery performance. VM-NSP and its implementation bM-NSP form the first vertical representation-based approach for complete NSP mining with LNEC. Theoretical analyses and experiments confirm the performance superiority of bM-NSP on synthetic and real-life datasets w.r.t. diverse data factors, which substantially expands existing NSP mining methods towards flexible NSP discovery.

 
An Efficient Method for Modeling Non-occurring Behaviors by Negative Sequential Patterns with Loose Constraints
Ping Qiu, Yongshun Gong, Yuhai Zhao, Longbing Cao, Chengqi Zhang, Xiangjun Dong. access the paper, IEEE Transactions on Neural Networks and Learning Systems, 10.1109/TNNLS.2021.3063162, 2021

Non-occurring behaviors analysis is recognized as a latest research domain to capture the negative (hidden) sequential patterns (NSPs) from the real world. These hidden patterns represent a new perspective for serving some complex behaviors, such as insurance fraud detection and medical diagnosis analysis. Due to the instinct complexities of nonoccurring problem, most NSP mining algorithms exploit the strict constraints to simplify the formulation and reduce the computational cost. However, such constraints restrict the flexibility of NSPs that cannot expose the hidden behavior comprehensively. Motivated by this point, in this paper, we loosen some inflexible constraints and solve a series of consequent challenging problems. In details, firstly, we give a new definition of negative containment with set theory according to the loosen constraints. Secondly, an efficient method to fast calculate the supports of negative sequences is designed. The method only uses the information of corresponding positive sequential patterns (PSPs), avoiding additional database scans. Finally, a novel and efficient algorithm, NegI-NSP, is proposed to efficiently identify the high valuable NSPs. Theoretical analyses, comparisons and experiments on three synthetic and one real-life datasets clearly show that the proposed method NegI-NSP can efficiently discover more valuable patterns.