Computational Advertising

Click-Through Rate Prediction

Online advertising allows advertisers to only bid and pay for measurable user responses, such as clicks on ads. As a consequence, click prediction systems are central to most on-line advertising systems. We introduce a new Bayesian click-through rate (CTR) prediction algorithm based on a probit regression model that maps discrete or real-valued input features to probabilities. It maintains Gaussian beliefs over weights of the model and performs Gaussian online updates derived from approximate message passing. Scalability of the algorithm is ensured through a principled weight pruning procedure and an approximate parallel implementation. In practice, the model combines decision trees with logistic regression, outperforming either of these methods on its own. The most important thing is to have the right features: those capturing historical information about the user or ad dominate other types of features. Picking the optimal handling for data freshness, learning rate schema and data sampling improve the model slightly, though much less than adding a high-value feature, or picking the right model to begin with.


He, Xinran; Pan, Junfeng; Jin, Ou; Xu, Tianbing; Liu, Bo; Xu, Tao; Shi, Yanxin; Atallah, Antoine; Herbrich, Ralf; Bowers, Stuart; Candela, Joaquin Quiñonero

Practical Lessons from Predicting Clicks on Ads at Facebook Inproceedings

In: Proceedings of 20th ACM SIGKDD Conference on Knowledge Discovery and Data Mining, pp. 1–9, ACM 2014.

Abstract | Links | BibTeX


Graepel, Thore; Candela, Joaquin Quiñonero; Borchert, Thomas; Herbrich, Ralf

Web-Scale Bayesian Click-Through Rate Prediction for Sponsored Search Advertising in Microsoft's Bing Search Engine Inproceedings

In: Proceedings of the 27th International Conference on Machine Learning, pp. 13–20, 2010.

Abstract | Links | BibTeX

Keyword Suggestions

We developed an efficient Bayesian online learning algorithm for clustering advertisements based on the keywords they have been subscribed to. The proposed approach scales well for large datasets, and compares favorably to other clustering algorithms on advertisements. As a concrete application to online advertising, we show how the learned model can be used to recommend new keywords for given advertisements.


Schwaighofer, Anton; Candela, Joaquin Quiñonero; Borchert, Thomas; Graepel, Thore; Herbrich, Ralf

Scalable Clustering and Keyword Suggestion for Online Advertisements Inproceedings

In: Proceedings of 3rd Annual International Workshop on Data Mining and Audience Intelligence for Advertising, pp. 27–36, 2009.

Abstract | Links | BibTeX