Beyond Next Item Recommendation: Recommending and Evaluating List of Sequences

Abstract

Recommender systems (RS) suggest items-based on the estimated preferences of users. Recent RS methods utilise vector space embeddings and deep learning methods to make efficient recommendations. However, most of these methods overlook the sequentiality feature and consider each interaction, e.g., check-in, independent from each other. The proposed method considers the sequentiality of the interactions of users with items and uses them to make recommendations of a list of multi-item sequences. The proposed method uses FastText \cite{bojanowski2016enriching}, a well-known technique in natural language processing (NLP), to model the relationship among the subunits of sequences, e.g., tracks, playlists, and utilises the trained representation as an input to a traditional recommendation method. The recommended lists of multi-item sequences are evaluated by the ROUGE \cite{lin2003automatic,lin2004rouge} metric, which is also commonly used in the NLP literature. The current experimental results reveal that it is possible to recommend a list of multi-item sequences, in addition to the traditional next item recommendation. Also, the usage of FastText, which utilise sub-units of the input sequences, helps to overcome cold-start user problem.

References in corpus (9)

• Distributed Representations of Sentences and Documents
• BPR: Bayesian Personalized Ranking from Implicit Feedback
• Learning over Knowledge-Base Embeddings for Recommendation
• Learning Heterogeneous Knowledge Base Embeddings for Explainable Recommendation
• Enriching Word Vectors with Subword Information
• From Word Embeddings to Item Recommendation
• Collaborative Deep Learning for Recommender Systems
• Modelling User Preferences using Word Embeddings for Context-Aware Venue Recommendation
• GT-SEER: Geo-Temporal SEquential Embedding Rank for Point-of-interest Recommendation