The Continuous Cold-start Problem in e-Commerce Recommender Systems

Many e-commerce websites use recommender systems to recommend items to users. When a user or item is new, the system may fail because not enough information is available on this user or item. Various solutions to this `cold-start problem' have been proposed in the literature. However, many real-life e-commerce applications suffer from an aggravated, recurring version of cold-start even for known users or items, since many users visit the website rarely, change their interests over time, or exhibit different personas. This paper exposes the `Continuous Cold Start' (CoCoS) problem and its consequences for content- and context-based recommendation from the viewpoint of typical e-commerce applications, illustrated with examples from a major travel recommendation website, Booking.com. Keywords: Recommender systems, continous cold-start problem, industrial applications

[1]  Yehuda Koren,et al.  Collaborative filtering with temporal dynamics , 2009, KDD.

[2]  Gediminas Adomavicius,et al.  Toward the next generation of recommender systems: a survey of the state-of-the-art and possible extensions , 2005, IEEE Transactions on Knowledge and Data Engineering.

[3]  Ulf Brefeld,et al.  Factored MDPs for detecting topics of user sessions , 2014, RecSys '14.

[4]  Ee-Peng Lim,et al.  Modeling Temporal Adoptions Using Dynamic Matrix Factorization , 2013, 2013 IEEE 13th International Conference on Data Mining.

[5]  Sean M. McNee,et al.  Getting to know you: learning new user preferences in recommender systems , 2002, IUI '02.

[6]  Liang Tang,et al.  Ensemble contextual bandits for personalized recommendation , 2014, RecSys '14.

[7]  Gediminas Adomavicius,et al.  Context-aware recommender systems , 2008, RecSys '08.

[8]  Michael C. Mozer,et al.  Detecting Topic Drift with Compound Topic Models , 2009, ICWSM.

[9]  Amin Mantrach,et al.  Item cold-start recommendations: learning local collective embeddings , 2014, RecSys '14.

[10]  Maria Fasli,et al.  Utilizing contextual ontological user profiles for personalized recommendations , 2014, Expert Syst. Appl..

[11]  Martha Larson,et al.  CARS2: Learning Context-aware Representations for Context-aware Recommendations , 2014, CIKM.

[12]  Kush R. Varshney,et al.  Dynamic matrix factorization: A state space approach , 2011, 2012 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP).

[13]  Liron Levin,et al.  OFF-set: one-pass factorization of feature sets for online recommendation in persistent cold start settings , 2013, RecSys.

[14]  Ido Guy,et al.  Personalized recommendation of social software items based on social relations , 2009, RecSys '09.

[15]  Bradley N. Miller,et al.  Social Information Filtering : Algorithms for Automating “ Word of Mouth , ” , 2017 .

[16]  Scott Sanner,et al.  Social collaborative filtering for cold-start recommendations , 2014, RecSys '14.

[17]  Joseph A. Konstan,et al.  Evaluating recommender behavior for new users , 2014, RecSys '14.

[18]  John Riedl,et al.  GroupLens: an open architecture for collaborative filtering of netnews , 1994, CSCW '94.

[19]  David M. Pennock,et al.  Categories and Subject Descriptors , 2001 .