skip to main content
10.1145/2648584.2648589acmconferencesArticle/Chapter ViewAbstractPublication PageskddConference Proceedingsconference-collections
tutorial

Practical Lessons from Predicting Clicks on Ads at Facebook

Published: 24 August 2014 Publication History

Abstract

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 online advertising systems. With over 750 million daily active users and over 1 million active advertisers, predicting clicks on Facebook ads is a challenging machine learning task. In this paper we introduce a model which combines decision trees with logistic regression, outperforming either of these methods on its own by over 3%, an improvement with significant impact to the overall system performance. We then explore how a number of fundamental parameters impact the final prediction performance of our system. Not surprisingly, the most important thing is to have the right features: those capturing historical information about the user or ad dominate other types of features. Once we have the right features and the right model (decisions trees plus logistic regression), other factors play small roles (though even small improvements are important at scale). 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.

References

[1]
R. Ananthanarayanan, V. Basker, S. Das, A. Gupta, H. Jiang, T. Qiu, A. Reznichenko, D. Ryabkov, M. Singh, and S. Venkataraman. Photon: Fault-tolerant and scalable joining of continuous data streams. In SIGMOD, 2013.
[2]
L. Bottou. Online algorithms and stochastic approximations. In D. Saad, editor, Online Learning and Neural Networks. Cambridge University Press, Cambridge, UK, 1998. revised, oct 2012.
[3]
O. Chapelle and L. Li. An empirical evaluation of thompson sampling. In Advances in Neural Information Processing Systems, volume 24, 2012.
[4]
B. Edelman, M. Ostrovsky, and M. Schwarz. Internet advertising and the generalized second price auction: Selling billions of dollars worth of keywords. In American Economic Review, volume 97, pages 242--259, 2007.
[5]
J. H. Friedman. Greedy function approximation: A gradient boosting machine. Annals of Statistics, 29:1189--1232, 1999.
[6]
L. Golab and M. T. Özsu. Processing sliding window multi-joins in continuous queries over data streams. In VLDB, pages 500--511, 2003.
[7]
T. Graepel, J. Quiñonero 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, pages 13--20, 2010.
[8]
H. B. McMahan, G. Holt, D. Sculley, M. Young, D. Ebner, J. Grady, L. Nie, T. Phillips, E. Davydov, D. Golovin, S. Chikkerur, D. Liu, M. Wattenberg, A. M. Hrafnkelsson, T. Boulos, and J. Kubica. Ad click prediction: a view from the trenches. In KDD, 2013.
[9]
M. Richardson, E. Dominowska, and R. Ragno. Predicting clicks: Estimating the click-through rate for new ads. In WWW, pages 521--530, 2007.
[10]
A. Thusoo, S. Antony, N. Jain, R. Murthy, Z. Shao, D. Borthakur, J. Sarma, and H. Liu. Data warehousing and analytics infrastructure at facebook. In SIGMOD, pages 1013--1020, 2010.
[11]
H. R. Varian. Position auctions. In International Journal of Industrial Organization, volume 25, pages 1163--1178, 2007.
[12]
J. Yi, Y. Chen, J. Li, S. Sett, and T. W. Yan. Predictive model performance: Offline and online evaluations. In KDD, pages 1294--1302, 2013.

Cited By

View all
  • (2025)Applying Machine Learning to Preselective Weighing of Moving VehiclesApplied Sciences10.3390/app1504174315:4(1743)Online publication date: 8-Feb-2025
  • (2025)Modyn: Data-Centric Machine Learning Pipeline OrchestrationProceedings of the ACM on Management of Data10.1145/37097053:1(1-30)Online publication date: 11-Feb-2025
  • (2025)Hyperbolic Graph Contrastive Learning for Collaborative FilteringIEEE Transactions on Knowledge and Data Engineering10.1109/TKDE.2024.352296037:3(1255-1267)Online publication date: Mar-2025
  • Show More Cited By

Recommendations

Comments

Information & Contributors

Information

Published In

cover image ACM Conferences
ADKDD'14: Proceedings of the Eighth International Workshop on Data Mining for Online Advertising
August 2014
65 pages
ISBN:9781450329996
DOI:10.1145/2648584
Permission to make digital or hard copies of all or part of this work for personal or classroom use is granted without fee provided that copies are not made or distributed for profit or commercial advantage and that copies bear this notice and the full citation on the first page. Copyrights for components of this work owned by others than ACM must be honored. Abstracting with credit is permitted. To copy otherwise, or republish, to post on servers or to redistribute to lists, requires prior specific permission and/or a fee. Request permissions from [email protected]

Sponsors

Publisher

Association for Computing Machinery

New York, NY, United States

Publication History

Published: 24 August 2014

Permissions

Request permissions for this article.

Check for updates

Qualifiers

  • Tutorial
  • Research
  • Refereed limited

Conference

KDD '14
Sponsor:

Acceptance Rates

Overall Acceptance Rate 12 of 21 submissions, 57%

Upcoming Conference

KDD '25

Contributors

Other Metrics

Bibliometrics & Citations

Bibliometrics

Article Metrics

  • Downloads (Last 12 months)499
  • Downloads (Last 6 weeks)32
Reflects downloads up to 16 Feb 2025

Other Metrics

Citations

Cited By

View all
  • (2025)Applying Machine Learning to Preselective Weighing of Moving VehiclesApplied Sciences10.3390/app1504174315:4(1743)Online publication date: 8-Feb-2025
  • (2025)Modyn: Data-Centric Machine Learning Pipeline OrchestrationProceedings of the ACM on Management of Data10.1145/37097053:1(1-30)Online publication date: 11-Feb-2025
  • (2025)Hyperbolic Graph Contrastive Learning for Collaborative FilteringIEEE Transactions on Knowledge and Data Engineering10.1109/TKDE.2024.352296037:3(1255-1267)Online publication date: Mar-2025
  • (2025)A Lightweight Knowledge Distillation and Feature Compression Model for User Click-Through Rates Prediction in Edge Computing ScenariosIEEE Internet of Things Journal10.1109/JIOT.2024.344664012:3(2295-2308)Online publication date: 1-Feb-2025
  • (2025)CoreNet: Leveraging context-aware representations via MLP networks for CTR predictionKnowledge-Based Systems10.1016/j.knosys.2025.113154312(113154)Online publication date: Mar-2025
  • (2024)Actions speak louder than wordsProceedings of the 41st International Conference on Machine Learning10.5555/3692070.3694484(58484-58509)Online publication date: 21-Jul-2024
  • (2024)Non-stationary online convex optimization with arbitrary delaysProceedings of the 41st International Conference on Machine Learning10.5555/3692070.3694115(49991-50011)Online publication date: 21-Jul-2024
  • (2024)A field guide for pacing budget and ROS constraintsProceedings of the 41st International Conference on Machine Learning10.5555/3692070.3692175(2607-2638)Online publication date: 21-Jul-2024
  • (2024)KGCFRec: Improving Collaborative Filtering Recommendation with Knowledge GraphElectronics10.3390/electronics1310192713:10(1927)Online publication date: 15-May-2024
  • (2024)Fusion of GBDT and neural network for click-through rate estimationJournal of Intelligent & Fuzzy Systems10.3233/JIFS-234713(1-13)Online publication date: 16-Mar-2024
  • Show More Cited By

View Options

Login options

View options

PDF

View or Download as a PDF file.

PDF

eReader

View online with eReader.

eReader

Figures

Tables

Media

Share

Share

Share this Publication link

Share on social media