ABSTRACT
The vast majority of recommender systems model preferences as static or slowly changing due to observable user experience. However, spontaneous changes in user preferences are ubiquitous in many domains like media consumption and key factors that drive changes in preferences are not directly observable. These latent sources of preference change pose new challenges. When systems do not track and adapt to users' tastes, users lose confidence and trust, increasing the risk of user churn. We meet these challenges by developing a model of novelty preferences that learns and tracks latent user tastes. We combine three innovations: a new measure of item similarity based on patterns of consumption co-occurrence; model for spontaneous changes in preferences; and a learning agent that tracks each user's dynamic preferences and learns individualized policies for variety. The resulting framework adaptively provides users with novelty tailored to their preferences for change per se.
- 2016. Netflix's Grand, Daring, Maybe Crazy Plan to Conquer the World. (2016). http://www.wired.com/2016/03/netflixs-grand-maybe-crazy-plan-conquer-world/Google Scholar
- Fabian Abel, Eelco Herder, Geert-Jan Houben, Nicola Henze, and Daniel Krause. 2013. Cross-system user modeling and personalization on the social web. User Modeling and User-Adapted Interaction 23, 2--3 (2013), 169--209.Google ScholarCross Ref
- D.E. Berlyne. 1960. Conflict, Arousal and Curiosity. McGraw-Hill.Google Scholar
- David M Blei, Andrew Y Ng, and Michael I Jordan. 2003. Latent dirichlet allocation. the Journal of machine Learning research 3 (2003), 993--1022. Google ScholarDigital Library
- O. Celma. 2010. Music Recommendation and Discovery in the Long Tail. Springer. Google ScholarDigital Library
- Jonathan D Cohen, Samuel M McClure, and Angela J Yu. 2007. Should I stay or should I go? How the human brain manages the trade-off between exploitation and exploration. Philosophical Transactions of the Royal Society of London B: Biological Sciences 362, 1481 (2007), 933--942.Google ScholarCross Ref
- Lda developers. 2015. LDA Python. (2015). https://pypi.python.org/pypi/ldaGoogle Scholar
- Eyal Even-Dar and Yishay Mansour. 2004. Learning rates for Q-learning. The Journal of Machine Learning Research 5 (2004), 1--25. Google ScholarDigital Library
- P James Geiwitz. 1966. Structure of boredom. Journal of Personality and Social Psychology 3, 5 (1966), 592.Google ScholarCross Ref
- Moshe Givon. 1984. Variety seeking through brand switching. Marketing Science 3, 1 (1984), 1--22. Google ScholarDigital Library
- Thomas Goetz, Anne C. Frenzel, Nathan C. Hall, Ulrike E. Nett, Reinhard Pekrun, and Anastasiya A. Lipnevich. 2013. Types of boredom: An experience sampling approach. Motivation and Emotion 38, 3 (2013), 401--419.Google ScholarCross Ref
- Abel P Jeuland. 1979. Brand choice inertia as one aspect of the notion of brand loyalty. Management Science 25, 7 (1979), 671--682.Google ScholarCross Ref
- Leslie Pack Kaelbling, Michael L Littman, and Andrew W Moore. 1996. Reinforcement learning: A survey. Journal of artificial intelligence research (1996), 237--285. Google ScholarDigital Library
- Komal Kapoor, Vikas Kumar, Loren G. Terveen, Joseph A. Konstan, and Paul R. Schrater. 2015. "I like to explore sometimes": Adapting to Dynamic User Novelty Preferences.. In RecSys, Hannes Werthner, Markus Zanker, Jennifer Golbeck, and Giovanni Semeraro (Eds.). ACM, 19--26. Google ScholarDigital Library
- Komal Kapoor, Nisheeth Srivastava, Jaideep Srivastava, and Paul Schrater. 2013. Measuring spontaneous devaluations in user preferences. In Proceedings of the 19th ACM SIGKDD international conference on Knowledge discovery and data mining. ACM, 1061--1069. Google ScholarDigital Library
- Last.fm. 2015. last.fm. (2015). http://www.last.fmGoogle Scholar
- Neal Lathia, Stephen Hailes, Licia Capra, and Xavier Amatriain. 2010. Temporal Diversity in Recommender Systems. In Proceedings of the 33rd International ACM SIGIR Conference on Research and Development in Information Retrieval (SIGIR '10). ACM, NY, NY, USA, 210--217. Google ScholarDigital Library
- Neal Kiritkumar Lathia. 2010. Evaluating collaborative filtering over time. Ph.D. Dissertation. University College London.Google Scholar
- Pei Lee, Laks V.S. Lakshmanan, Mitul Tiwari, and Sam Shah. 2014. Modeling Impression Discounting in Large-scale Recommender Systems. In Proceedings of the 20th ACM SIGKDD International Conference on Knowledge Discovery and Data Mining (KDD '14). ACM, NY, NY, USA, 1837--1846. Google ScholarDigital Library
- Edgar Pessemier Leigh McAlister. 1982. Variety Seeking Behavior: An Interdisciplinary Review. Journal of Consumer Research 9, 3 (1982), 311--322. http://www.jstor.org/stable/2488626Google ScholarCross Ref
- Joshua L Moore, Shuo Chen, Douglas Turnbull, and Thorsten Joachims. 2013. Taste Over Time: The Temporal Dynamics of User Preferences.. In ISMIR. Citeseer, 401--406.Google Scholar
- Sean A. Munson and Paul Resnick. 2010. Presenting Diverse Political Opinions: How and How Much. In Proceedings of the SIGCHI Conference on Human Factors in Computing Systems (CHI '10). ACM, NY, NY, USA, 1457--1466. Google ScholarDigital Library
- Ulrike E. Nett, Thomas Goetz, and Lia M. Daniels. 2010. What to do when feeling bored?: Students' strategies for coping with boredom. Learning and Individual Differences 20, 6 (2010), 626 -- 638.Google ScholarCross Ref
- Badrul Sarwar, George Karypis, Joseph Konstan, and John Riedl. 2001. Item-based collaborative filtering recommendation algorithms. In Proceedings of the 10th international conference on World Wide Web. ACM, 285--295. Google ScholarDigital Library
- R.S. Sutton and A.G. Barto. 1998. Reinforcement learning: An introduction. Vol. 116. Cambridge Univ Press. Google ScholarDigital Library
- Aaron van den Oord, Sander Dieleman, and Benjamin Schrauwen. 2013. Deep content-based music recommendation. In Advances in Neural Information Processing Systems 26, C. J. C. Burges, L. Bottou, M. Welling, Z. Ghahramani, and K. Q. Weinberger (Eds.). Curran Associates, Inc., 2643--2651. http://papers.nips.cc/paper/ 5004-deep-content-based-music-recommendation.pdf Google ScholarDigital Library
- Saúl Vargas and Pablo Castells. 2011. Rank and Relevance in Novelty and Diversity Metrics for Recommender Systems. In Proceedings of the Fifth ACM Conference on Recommender Systems (RecSys '11). ACM, NY, NY, USA, 109--116. Google ScholarDigital Library
- Stephen J Vodanovich. 2003. Psychometric measures of boredom: A review of the literature. The Journal of psychology 137, 6 (2003), 569--595.Google ScholarCross Ref
- Hongzhi Yin, Bin Cui, Ling Chen, Zhiting Hu, and Zi Huang. 2014. A temporal context-aware model for user behavior modeling in social media systems. In Proceedings of the 2014 ACM SIGMOD international conference on Management of data. ACM, 1543--1554. Google ScholarDigital Library
Index Terms
- Novelty Learning via Collaborative Proximity Filtering
Recommendations
How Much Novelty is Relevant?: It Depends on Your Curiosity
SIGIR '16: Proceedings of the 39th International ACM SIGIR conference on Research and Development in Information RetrievalTraditional recommendation systems (RS's) aim to recommend items that are relevant to the user's interest. Unfortunately, the recommended items will soon become too familiar to the user and hence fail to arouse her interest. Discovery-oriented ...
Trust-based collaborative filtering: tackling the cold start problem using regular equivalence
RecSys '18: Proceedings of the 12th ACM Conference on Recommender SystemsUser-based Collaborative Filtering (CF) is one of the most popular approaches to create recommender systems. This approach is based on finding the most relevant k users from whose rating history we can extract items to recommend. CF, however, suffers ...
Investigating serendipity in recommender systems based on real user feedback
SAC '18: Proceedings of the 33rd Annual ACM Symposium on Applied ComputingOver the past several years, research in recommender systems has emphasized the importance of serendipity, but there is still no consensus on the definition of this concept and whether serendipitous items should be recommended is still not a well-...
Comments