Predictive client-side profiles for personalized advertising

Personalization is ubiquitous in modern online applications as it provides significant improvements in user experience by adapting it to inferred user preferences. However, there are increasing concerns related to issues of privacy and control of the user data that is aggregated by online systems to power personalized experiences. These concerns are particularly significant for user profile aggregation in online advertising. This paper describes a practical, learning-driven client-side personalization approach for keyword advertising platforms, an emerging application previously not addressed in literature. Our approach relies on storing user-specific information entirely within the user's control (in a browser cookie or browser local storage), thus allowing the user to view, edit or purge it at any time (e.g., via a dedicated webpage). We develop a principled, utility-based formulation for the problem of iteratively updating user profiles stored client-side, which relies on calibrated prediction of future user activity. While optimal profile construction is NP-hard for pay-per-click advertising with bid increments, it can be efficiently solved via a greedy approximation algorithm guaranteed to provide a near-optimal solution due to the fact that keyword profile utility is submodular: it exhibits the property of diminishing returns with increasing profile size. We empirically evaluate client-side keyword profiles for keyword advertising on a large-scale dataset from a major search engine. Experiments demonstrate that predictive client-side personalization allows ad platforms to retain almost all of the revenue gains from personalization even if they give users the freedom to opt out of behavior tracking backed by server-side storage. Additionally, we show that advertisers can potentially increase their return on investment significantly by utilizing bid increments for keyword profiles in their ad campaigns.

[1]  Helen Nissenbaum,et al.  Adnostic: Privacy Preserving Targeted Advertising , 2010, NDSS.

[2]  Erick Cantú-Paz,et al.  Personalized click prediction in sponsored search , 2010, WSDM '10.

[3]  Jaime Teevan,et al.  Implicit feedback for inferring user preference: a bibliography , 2003, SIGF.

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

[5]  Kamesh Munagala,et al.  Hybrid keyword search auctions , 2008, WWW '09.

[6]  Feng Qiu,et al.  Automatic identification of user interest for personalized search , 2006, WWW '06.

[7]  John F. Canny,et al.  Factor Modeling for Advertisement Targeting , 2009, NIPS.

[8]  Filip Radlinski,et al.  Personalizing web search using long term browsing history , 2011, WSDM '11.

[9]  Zheng Chen,et al.  A Markov chain model for integrating behavioral targeting into contextual advertising , 2009, KDD Workshop on Data Mining and Audience Intelligence for Advertising.

[10]  Eugene Agichtein,et al.  Ready to buy or just browsing?: detecting web searcher goals from interaction data , 2010, SIGIR.

[11]  Samir Khuller,et al.  The Budgeted Maximum Coverage Problem , 1999, Inf. Process. Lett..

[12]  John Riedl.  Guest Editor's Introduction: Personalization and Privacy , 2001, IEEE Internet Comput..

[13]  Ke Wang,et al.  Privacy-enhancing personalized web search , 2007, WWW '07.

[14]  Andreas Krause,et al.  A Utility-Theoretic Approach to Privacy and Personalization , 2008, AAAI.

[15]  Ji-Rong Wen,et al.  WWW 2007 / Track: Search Session: Personalization A Largescale Evaluation and Analysis of Personalized Search Strategies ABSTRACT , 2022 .

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

[17]  Paul R. Milgrom,et al.  A theory of auctions and competitive bidding , 1982 .

[18]  J. Friedman.  Greedy function approximation: A gradient boosting machine. , 2001 .

[19]  John F. Canny,et al.  Large-scale behavioral targeting , 2009, KDD.

[20]  Saikat Guha,et al.  Serving Ads from localhost for Performance, Privacy, and Profit , 2009, HotNets.

[21]  Masatoshi Yoshikawa,et al.  Adaptive web search based on user profile constructed without any effort from users , 2004, WWW '04.

[22]  Wen Zhang,et al.  How much can behavioral targeting help online advertising? , 2009, WWW '09.

[23]  Jianfeng Gao,et al.  Scalable training of L1-regularized log-linear models , 2007, ICML '07.

[24]  Ryen W. White,et al.  Talking the talk vs. walking the walk: salience of information needs in querying vs. browsing , 2008, SIGIR '08.

[25]  Foster Provost,et al.  Audience selection for on-line brand advertising: privacy-friendly social network targeting , 2009, KDD.

[26]  Benjamin M. Marlin,et al.  Modeling User Rating Profiles For Collaborative Filtering , 2003, NIPS.

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

[28]  Matthew Richardson,et al.  Catching the drift: learning broad matches from clickthrough data , 2009, KDD.

[29]  Susan T. Dumais,et al.  Personalizing Search via Automated Analysis of Interests and Activities , 2005, SIGIR.

[30]  Andreas Krause,et al.  Cost-effective outbreak detection in networks , 2007, KDD '07.

[31]  Alfred Kobsa,et al.  Privacy-enhanced personalization , 2006, FLAIRS.

[32]  Michael Collins,et al.  Discriminative Training Methods for Hidden Markov Models: Theory and Experiments with Perceptron Algorithms , 2002, EMNLP.

[33]  Yoichi Shinoda,et al.  Information filtering based on user behavior analysis and best match text retrieval , 1994, SIGIR '94.

[34]  Matt Fredrikson,et al.  RePriv: Re-Envisioning In-Browser Privacy , 2011 .

[35]  Zhenglu Yang,et al.  Dynamic Adaptation Strategies for Long-Term and Short-Term User Profile to Personalize Search , 2007, APWeb/WAIM.

[36]  M. L. Fisher,et al.  An analysis of approximations for maximizing submodular set functions—I , 1978, Math. Program..