ABSTRACT
We describe a new approach to solving the click-through rate (CTR) prediction problem in sponsored search by means of MatrixNet, the proprietary implementation of boosted trees. This problem is of special importance for the search engine, because choosing the ads to display substantially depends on the predicted CTR and greatly affects the revenue of the search engine and user experience. We discuss different issues such as evaluating and tuning MatrixNet algorithm, feature importance, performance, accuracy and training data set size. Finally, we compare MatrixNet with several other methods and present experimental results from the production system.
- K. Bauman, A. Kornetova, V. Topinsky, and D. Leshiner. Ctr prediction based on click statistic. In Workshop: Machine Learning in Online Advertising, pages 8--13. NIPS, December 2010.Google Scholar
- A. Broder and V. Josifovski. Introduction to Computational Advertising. http://www.stanford.edu/class/msande239/.Google Scholar
- K. Dave and V. Varma. Optimizing display advertisements based on historic user trails. In WWW, 2011.Google Scholar
- K. Dembczynski, W. Kotlowski, and D. Weiss. Predicting ads' click-through rate with decision rules. In WWW, April 2008.Google Scholar
- B. Edelman, M. Ostrovsky, and M. Schwarz. Internet advertising and the generalized second price auction: Selling billions of dollars worth of keywords. American Economic Review, 97(1):242--259, 2007.Google Scholar
- J. Friedman. Greedy function approximation: A gradient boosting machine. In Techical Report. Dept. of Statistics, Stanford University, 1999.Google Scholar
- J. Friedman. Stochastic gradient boosting. Computational Statistics and Data Analysis, (38):367--378, 2002. Google ScholarDigital Library
- T. Graepel, J. Q. Candela, T. Borchert, and R. Herbrich. Web-scale bayesian click-through rate prediction for sponsored search advertising in microsoft's bing search engine. In ICML, 2010.Google ScholarDigital Library
- A. Gulin. Matrixnet. Technical report, http://www.ashmanov.com/arc/searchconf2010/08gulin-searchconf2010.ppt, 2010. (in russian).Google Scholar
- A. Gulin, I. Kuralenok, and D. Pavlov. Winning the transfer learning track of yahoo!'s learning to rank challenge with yetirank. In Workshop and Conference Proceedings, pages 63--76. JMLR, 2011.Google Scholar
- T. Hastie, R. Tibshirani, and J. Friedman. The Elements of Statistical Learning. Springer-Verlag, New York, 2001.Google ScholarCross Ref
- T. Lumley. biglm: bounded memory linear and generalized linear models, 2011. R package version 0.8.Google Scholar
- R Development Core Team. R: A Language and Environment for Statistical Computing. R Foundation for Statistical Computing, Vienna, Austria, 2011. ISBN 3-900051-07-0.Google Scholar
- M. Richardson, E. Dominowska, and R. Ragno. Predicting clicks: Estimating the click-through rate for new ads. In WWW. ACM Press, 2007. Google ScholarDigital Library
- G. Ridgeway. gbm: Generalized Boosted Regression Models, 2010. R package version 1.6--3.1.Google Scholar
- Z. A. Zhu, W. Chen, T. Minka, C. Zhu, and Z. Chen. A novel click model and its applications to online advertising. In WSDM, 2010. Google ScholarDigital Library
Index Terms
- Using boosted trees for click-through rate prediction for sponsored search
Recommendations
Predicting clicks: estimating the click-through rate for new ads
WWW '07: Proceedings of the 16th international conference on World Wide WebSearch engine advertising has become a significant element of the Web browsing experience. Choosing the right ads for the query and the order in which they are displayed greatly affects the probability that a user will see and click on each ad. This ...
Predicting CTR of new ads via click prediction
CIKM '12: Proceedings of the 21st ACM international conference on Information and knowledge managementPredicting CTR of ads on the search result page is an urgent topic. The reason for this is that choosing the right advertisement greatly affects revenue of the search engine and advertisers and user's satisfaction. For ads with the large click history ...
New features for query dependent sponsored search click prediction
WWW '13 Companion: Proceedings of the 22nd International Conference on World Wide WebClick prediction for sponsored search is an important problem for commercial search engines. Good click prediction algorithm greatly affects on the revenue of the search engine, user experience and brings more clicks to landing pages of advertisers. ...
Comments