Improving ad relevance in sponsored search

We describe a machine learning approach for predicting sponsored search ad relevance. Our baseline model incorporates basic features of text overlap and we then extend the model to learn from past user clicks on advertisements. We present a novel approach using translation models to learn user click propensity from sparse click logs. Our relevance predictions are then applied to multiple sponsored search applications in both offline editorial evaluations and live online user tests. The predicted relevance score is used to improve the quality of the search page in three areas: filtering low quality ads, more accurate ranking for ads, and optimized page placement of ads to reduce prominent placement of low relevance ads. We show significant gains across all three tasks.

[1]  Wei Vivian Zhang,et al.  Comparing Click Logs and Editorial Labels for Training Query Rewriting , 2007 .

[2]  Jaana Kekäläinen,et al.  Cumulated gain-based evaluation of IR techniques , 2002, TOIS.

[3]  Andrei Broder,et al.  A taxonomy of web search , 2002, SIGF.

[4]  Hema Raghavan,et al.  A relevance model based filter for improving ad quality , 2009, SIGIR.

[5]  T. Minka.  A comparison of numerical optimizers for logistic regression , 2004 .

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

[7]  Andrei Z. Broder,et al.  To swing or not to swing: learning when (not) to advertise , 2008, CIKM '08.

[8]  Joshua Goodman,et al.  Finding advertising keywords on web pages , 2006, WWW '06.

[9]  Qiang Wu,et al.  McRank: Learning to Rank Using Multiple Classification and Gradient Boosting , 2007, NIPS.

[10]  Tasos Anastasakos,et al.  A collaborative filtering approach to ad recommendation using the query-ad click graph , 2009, CIKM.

[11]  Benjamin Rey,et al.  Generating query substitutions , 2006, WWW '06.

[12]  Vassilis Plachouras,et al.  A noisy-channel approach to contextual advertising , 2007, ADKDD '07.

[13]  Vassilis Plachouras,et al.  Online learning from click data for sponsored search , 2008, WWW.

[14]  Vanessa Murdock,et al.  Aspects of sentence retrieval , 2007, SIGF.

[15]  W. Bruce Croft,et al.  Searching question and answer archives , 2007 .

[16]  Hema Raghavan.  Evaluating Vector-Space and Probabilistic Models for Query to Ad Matching , 2008 .

[17]  Hermann Ney,et al.  Improvements in Phrase-Based Statistical Machine Translation , 2004, NAACL.

[18]  Andrei Z. Broder,et al.  A semantic approach to contextual advertising , 2007, SIGIR.

[19]  Ron Kohavi,et al.  Practical guide to controlled experiments on the web: listen to your customers not to the hippo , 2007, KDD '07.

[20]  Olivier Chapelle,et al.  A dynamic bayesian network click model for web search ranking , 2009, WWW '09.

[21]  Robert L. Mercer,et al.  The Mathematics of Statistical Machine Translation: Parameter Estimation , 1993, CL.

[22]  W. Bruce Croft,et al.  Relevance-Based Language Models , 2001, SIGIR '01.

[23]  Yoram Singer,et al.  BoosTexter: A Boosting-based System for Text Categorization , 2000, Machine Learning.

[24]  David D. Lewis,et al.  The TREC-5 Filtering Track , 1996, TREC.

[25]  John D. Lafferty,et al.  Information Retrieval as Statistical Translation , 2017 .

[26]  Andrei Z. Broder,et al.  Efficient query evaluation using a two-level retrieval process , 2003, CIKM '03.

[27]  Berthier A. Ribeiro-Neto,et al.  Impedance coupling in content-targeted advertising , 2005, SIGIR '05.

[28]  Hongyuan Zha,et al.  A General Boosting Method and its Application to Learning Ranking Functions for Web Search , 2007, NIPS.

[29]  Thomas Hofmann,et al.  Learning to Rank with Nonsmooth Cost Functions , 2006, NIPS.

[30]  Andrei Z. Broder,et al.  Search advertising using web relevance feedback , 2008, CIKM '08.

[31]  J. J. Rocchio,et al.  Relevance feedback in information retrieval , 1971 .

[32]  Filip Radlinski,et al.  Optimizing relevance and revenue in ad search: a query substitution approach , 2008, SIGIR '08.

[33]  Matthew Richardson,et al.  Predicting clicks: estimating the click-through rate for new ads , 2007, WWW '07.

[34]  Bernard J. Jansen,et al.  Examining Searcher Perceptions of and Interactions with Sponsored Results , 2005 .

[35]  Rukmini Iyer,et al.  Data-driven text features for sponsored search click prediction , 2009, KDD Workshop on Data Mining and Audience Intelligence for Advertising.