Click shaping to optimize multiple objectives

Recommending 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 the starting point of a user's journey and subsequent downstream utilities such as time-spent and revenue are important. In this paper, we call the problem of recommending links to jointly optimize for clicks and post-click downstream utilities click shaping. We propose a multi-objective programming approach in which multiple objectives are modeled in a constrained optimization framework. Such a formulation can naturally incorporate various application-driven requirements. We study several variants that model different requirements as constraints and discuss some of the subtleties involved. We conduct our experiments on a large dataset from a real system by using a newly proposed unbiased evaluation methodology [17]. Through extensive experiments we quantify the tradeoff between different objectives under various constraints. Our experimental results show interesting characteristics of different formulations and our findings may provide valuable guidance to the design of recommendation engines for web portals.

[1]  Carlos Romero,et al.  GOAL PROGRAMMING AND MULTIPLE CRITERIA DECISION-MAKING IN FARM PLANNING: SOME EXTENSIONS , 1985 .

[2]  Anne S. Hawkins Bandit Problems—Sequential Allocation of Experiments , 1987 .

[3]  P. W. Jones,et al.  Bandit Problems, Sequential Allocation of Experiments , 1987 .

[4]  R. S. Laundy,et al.  Multiple Criteria Optimisation: Theory, Computation and Application , 1989 .

[5]  Inderjit S. Dhillon,et al.  Efficient Clustering of Very Large Document Collections , 2001 .

[6]  Robert L. Grossman,et al.  Data Mining for Scientific and Engineering Applications , 2001, Massive Computing.

[7]  Inderjit S. Dhillon,et al.  Concept Decompositions for Large Sparse Text Data Using Clustering , 2004, Machine Learning.

[8]  Peter Auer,et al.  Finite-time Analysis of the Multiarmed Bandit Problem , 2002, Machine Learning.

[9]  Mehryar Mohri,et al.  Multi-armed Bandit Algorithms and Empirical Evaluation , 2005, ECML.

[10]  Stephen P. Boyd,et al.  Convex Optimization , 2004, Algorithms and Theory of Computation Handbook.

[11]  Daniel C. Fain,et al.  Sponsored search: A brief history , 2006 .

[12]  Abhinandan Das,et al.  Google news personalization: scalable online collaborative filtering , 2007, WWW '07.

[13]  Susan A. Murphy,et al.  Monographs on statistics and applied probability , 1990 .

[14]  J. Langford,et al.  The Epoch-Greedy algorithm for contextual multi-armed bandits , 2007, NIPS 2007.

[15]  Deepak Agarwal,et al.  Online Models for Content Optimization , 2008, NIPS.

[16]  John Langford,et al.  Exploration scavenging , 2008, ICML '08.

[17]  D. Sculley,et al.  Predicting bounce rates in sponsored search advertisements , 2009, KDD.

[18]  Wei Chu,et al.  A case study of behavior-driven conjoint analysis on Yahoo!: front page today module , 2009, KDD.

[19]  Andreas Dengel,et al.  Segment-level display time as implicit feedback: a comparison to eye tracking , 2009, SIGIR.

[20]  Bee-Chung Chen,et al.  Explore/Exploit Schemes for Web Content Optimization , 2009, 2009 Ninth IEEE International Conference on Data Mining.

[21]  Deepak Agarwal,et al.  Spatio-temporal models for estimating click-through rate , 2009, WWW '09.

[22]  Jun Wang,et al.  Optimizing multiple objectives in collaborative filtering , 2010, RecSys '10.

[23]  Ryen W. White,et al.  Understanding web browsing behaviors through Weibull analysis of dwell time , 2010, SIGIR.

[24]  Sergei Vassilvitskii,et al.  Optimal online assignment with forecasts , 2010, EC '10.

[25]  Wei Chu,et al.  A contextual-bandit approach to personalized news article recommendation , 2010, WWW '10.

[26]  Maksims Volkovs,et al.  Learning to rank with multiple objective functions , 2011, WWW.

[27]  Wei Chu,et al.  Unbiased offline evaluation of contextual-bandit-based news article recommendation algorithms , 2010, WSDM '11.