Practical Lessons from Predicting Clicks on Ads at Facebook
Xinran He, Junfeng Pan, Ou Jin, Tianbing Xu, Bo Liu, Tao Xu, Yanxin Shi, Antoine Atallah, Stuart Bowers, Joaquin Quiñonero Candela 2014. (View Paper → )
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.
Machine Learning pipelines are complex, there’s a million things to do a million places you can spend your time looking for gains. This paper from Facebook showed that actually having the right features is the most important factor - so it’s definitely worth spending time on feature engineering.