A Multi-Objective Learning to re-Rank Approach to Optimize Online Marketplaces for Multiple Stakeholders

Multi-objective recommender systems address the difficult task of recommending items that are relevant to multiple, possibly conflicting, criteria. However these systems are most often designed to address the objective of one single stakeholder, typically, in online commerce, the consumers whose input and purchasing decisions ultimately determine the success of the recommendation systems. In this work, we address the multi-objective, multi-stakeholder, recommendation problem involving one or more objective(s) per stakeholder. In addition to the consumer stakeholder, we also consider two other stakeholders; the suppliers who provide the goods and services for sale and the intermediary who is responsible for helping connect consumers to suppliers via its recommendation algorithms. We analyze the multi-objective, multi-stakeholder, problem from the point of view of the online marketplace intermediary whose objective is to maximize its commission through its recommender system. We define a multi-objective problem relating all our three stakeholders which we solve with a novel learning-to-re-rank approach that makes use of a novel regularization function based on the Kendall tau correlation metric and its kernel version; given an initial ranking of item recommendations built for the consumer, we aim to re-rank it such that the new ranking is also optimized for the secondary objectives while staying close to the initial ranking. We evaluate our approach on a real-world dataset of hotel recommendations provided by Expedia where we show the effectiveness of our approach against a business-rules oriented baseline model.

[1]  Filip Radlinski,et al.  Search Engines that Learn from Implicit Feedback , 2007, Computer.

[2]  Deepak Agarwal,et al.  Click shaping to optimize multiple objectives , 2011, KDD.

[3]  Jaana Kekäläinen,et al.  IR evaluation methods for retrieving highly relevant documents , 2000, SIGIR Forum.

[4]  Zhaohui Zheng,et al.  Learning to re-rank web search results with multiple pairwise features , 2011, WSDM '11.

[5]  Christian Posse,et al.  Multiple objective optimization in recommender systems , 2012, RecSys.

[6]  Vidit Jain,et al.  Learning to re-rank: query-dependent image re-ranking using click data , 2011, WWW.

[7]  Jean-Philippe Vert,et al.  The Kendall and Mallows Kernels for Permutations , 2015, IEEE Transactions on Pattern Analysis and Machine Intelligence.

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

[9]  Yue Gao,et al.  Learning more powerful test statistics for click-based retrieval evaluation , 2010, SIGIR.

[10]  Filip Radlinski,et al.  Evaluating Search Engine Relevance with Click-Based Metrics , 2010, Preference Learning.

[11]  Michael Rabadi,et al.  Kernel Methods for Machine Learning , 2015 .

[12]  John Dines,et al.  Considering Supplier Relations and Monetization in Designing Recommendation Systems , 2016, RecSys.

[13]  Christopher J. C. Burges,et al.  From RankNet to LambdaRank to LambdaMART: An Overview , 2010 .

[14]  Andreas Krause,et al.  Online Learning of Assignments that Maximize Submodular Functions , 2009, ArXiv.

[15]  M. Kendall.  A NEW MEASURE OF RANK CORRELATION , 1938 .

[16]  Di He,et al.  A Game-Theoretic Machine Learning Approach for Revenue Maximization in Sponsored Search , 2013, IJCAI.

[17]  Qiang Wu,et al.  Learning to Rank Using an Ensemble of Lambda-Gradient Models , 2010, Yahoo! Learning to Rank Challenge.

[18]  Pinar Donmez,et al.  On the local optimality of LambdaRank , 2009, SIGIR.

[19]  Thorsten Joachims,et al.  Optimizing search engines using clickthrough data , 2002, KDD.

[20]  Brian D. Davison,et al.  Multi-objective optimization in learning to rank , 2011, SIGIR '11.

[21]  Eyke Hüllermeier,et al.  Pairwise Preference Learning and Ranking , 2003, ECML.

[22]  Filip Radlinski,et al.  How does clickthrough data reflect retrieval quality? , 2008, CIKM '08.

[23]  Paul N. Bennett,et al.  Robust ranking models via risk-sensitive optimization , 2012, SIGIR '12.

[24]  Gregory N. Hullender,et al.  Learning to rank using gradient descent , 2005, ICML.

[25]  Filip Radlinski,et al.  Query chains: learning to rank from implicit feedback , 2005, KDD '05.

[26]  Gediminas Adomavicius,et al.  Multi-Criteria Recommender Systems , 2011, Recommender Systems Handbook.

[27]  Yi Chang,et al.  Learning to rank with multi-aspect relevance for vertical search , 2012, WSDM '12.