ABSTRACT
Online content recommendation aims to identify trendy articles in a continuously changing dynamic content pool. Most of existing works rely on online user feedback, notably clicks, as the objective and maximize it by showing articles with highest click-through rates. Recently, click shaping was introduced to incorporate multiple objectives in a constrained optimization framework. The work showed that significant tradeoff among the competing objectives can be observed and thus it is important to consider multiple objectives. However, the proposed click shaping approach is segment-based and can only work with a few non-overlapping user segments. It remains a challenge of how to enable deep personalization in click shaping. In this paper, we tackle the challenge by proposing personalized click shaping. The main idea is to work with the Lagrangian duality formulation and explore strong convexity to connect dual and primal solutions. We show that our formulation not only allows efficient conversion from dual to primal for online personalized serving, but also enables us to solve the optimization faster by approximation. We conduct extensive experiments on a large real data set and our experimental results show that the personalized click shaping can significantly outperform the segmented one, while achieving the same ability to balance competing objectives.
- D. Agarwal and B.-C. Chen. Regression-based latent factor models. In KDD, 2009. Google ScholarDigital Library
- D. Agarwal, B.-C. Chen, and P. Elango. Spatio-temporal models for estimating click-through rate. In WWW, 2009. Google ScholarDigital Library
- D. Agarwal, B.-C. Chen, P. Elango, and et al. Online models for content optimization. In NIPS, 2008.Google Scholar
- D. Agarwal, B.-C. Chen, P. Elango, and X. Wang. Click shaping to optimize multiple objectives. In KDD, 2011. Google ScholarDigital Library
- P. Auer, N. Cesa-Bianchi, and P. Fischer. Finite-time analysis of the multiarmed bandit problem. Machine Learning, 2002. Google ScholarDigital Library
- D. A. Berry and B. Fristedt. Bandit Problems: Sequential Allocation of Experiments. Chapman and Hall, 1985.Google Scholar
- S. Boyd and L. Vandenberghe. Convex Optimization. Cambridge University Press, 2004. Google ScholarDigital Library
- G. Buscher, L. van Elst, and A. Dengel. Segment-level display time as implicit feedback: a comparison to eye tracking. In SIGIR, 2009. Google ScholarDigital Library
- Y. Chen, P. Berkhin, B. Anderson, and N. R. Devanur. Real-time bidding algorithms for performance-based display ad allocation. In KDD, 2011. Google ScholarDigital Library
- A. Das, M. Datar, A. Garg, and S. Rajaram. Google news personalization: scalable online collaborative filtering. In WWW, 2007. Google ScholarDigital Library
- R. Fain and J. Pederson. Sponsored search: A brief history. Bulletin of American Society of Information and Technology, 2006.Google ScholarCross Ref
- P. V. Hentenryck and R. Bent. Online Stochastic Combinatorial Optimization. The MIT Press, 2006. Google ScholarDigital Library
- J. L. Herlocker, J. A. Konstan, A. Borchers, and J. Riedl. An algorithmic framework for performing collaborative filtering. In SIGIR, 1999. Google ScholarDigital Library
- T. Jambor and J. Wang. Optimizing multiple objectives in collaborative filtering. In RecSys, 2010. Google ScholarDigital Library
- Y. Koren. Collaborative filtering with temporal dynamics. In KDD, 2009. Google ScholarDigital Library
- J. Langford and T. Zhang. The epoch-greedy algorithm for contextual multi-armed bandits. In NIPS, 2008.Google Scholar
- L. Li, W. Chu, J. Langford, and R. E. Schapire. A contextual-bandit approach to personalized news article recommendation. In WWW, 2010. Google ScholarDigital Library
- L. Li, W. Chu, J. Langford, and X. Wang. Unbiased offline evaluation of contextual-bandit-based news article recommendation algorithms. In WSDM, 2011. Google ScholarDigital Library
- L. Li, D. Wang, T. Li, D. Knox, and B. Padmanabhan. Scene: a scalable two-stage personalized news recommendation system. In SIGIR, 2011. Google ScholarDigital Library
- J. Liu, P. Dolan, and E. R. Pedersen. Personalized news recommendation based on click behavior. In IUI, 2010. Google ScholarDigital Library
- D. Sculley, R. G. Malkin, S. Basu, and R. J. Bayardo. Predicting bounce rates in sponsored search advertisements. In KDD, 2009. Google ScholarDigital Library
- D. H. Stern, R. Herbrich, and T. Graepel. Matchbox: large scale online bayesian recommendations. In WWW, 2009. Google ScholarDigital Library
- R. Steuer. Multi-criteria optimization: theory, computation, and application. Wiley, 1986.Google Scholar
- K. M. Svore, M. N. Volkovs, and C. J. C. Burges. Learning to rank with multiple objective functions. In WWW, 2011. Google ScholarDigital Library
- E. Vee, S. Vassilvitski, and J. Shanmugasundaran. Optimal online assignment with forecasts. In EC, 2010. Google ScholarDigital Library
- J. Vermorel and M. Mohri. Multi-armed bandit algorithms and empirical evaluation. In ECML, 2005. Google ScholarDigital Library
- Y. Zhang, J. P. Callan, and T. P. Minka. Novelty and redundancy detection in adaptive filtering. In SIGIR, 2002. Google ScholarDigital Library
Index Terms
- Personalized click shaping through lagrangian duality for online recommendation
Recommendations
Click shaping to optimize multiple objectives
KDD '11: Proceedings of the 17th ACM SIGKDD international conference on Knowledge discovery and data miningRecommending interesting content to engage users is important for web portals (e.g. AOL, MSN, Yahoo!, and many others). Existing approaches typically recommend articles to optimize for a single objective, i.e., number of clicks. However a click is only ...
Personalized news recommendation based on click behavior
IUI '10: Proceedings of the 15th international conference on Intelligent user interfacesOnline news reading has become very popular as the web provides access to news articles from millions of sources around the world. A key challenge of news websites is to help users find the articles that are interesting to read. In this paper, we ...
Generalized Collaborative Personalized Ranking for Recommendation
Web and Big DataAbstractData sparsity is a common problem in collaborative ranking for personalized recommendation with implicit feedback. Several previous work tried to ‘borrow’ feedback information from users’ neighborhood as their prior preferences to alleviate this ...
Comments