Cost-sensitive Learning for Utility Optimization in Online Advertising Auctions
Author:
Damien Lefortier, Facebook
Abstract:
One of the most challenging problems in computational advertising is the prediction of click-through and conversion rates for bidding in online advertising auctions. An unaddressed problem in previous approaches is the existence of highly non-uniform misprediction costs. While for model evaluation these costs have been taken into account through recently proposed business-aware offline metrics – such as the Utility metric which measures the impact on advertiser profit – this is not the case when training the models themselves. In this paper, to bridge the gap, we formally analyze the relationship between optimizing the Utility metric and the log loss, which is considered as one of the state-of-the-art approaches in conversion modeling. Our analysis motivates the idea of weighting the log loss with the business value of the predicted outcome. We present and analyze a new cost weighting scheme and show that significant gains in offline and online performance can be achieved.
More on http://www.kdd.org/kdd2017/
KDD2017 Conference is published on http://videolectures.net/
Видео Cost-sensitive Learning for Utility Optimization in Online Advertising Auctions канала KDD2017 video
Damien Lefortier, Facebook
Abstract:
One of the most challenging problems in computational advertising is the prediction of click-through and conversion rates for bidding in online advertising auctions. An unaddressed problem in previous approaches is the existence of highly non-uniform misprediction costs. While for model evaluation these costs have been taken into account through recently proposed business-aware offline metrics – such as the Utility metric which measures the impact on advertiser profit – this is not the case when training the models themselves. In this paper, to bridge the gap, we formally analyze the relationship between optimizing the Utility metric and the log loss, which is considered as one of the state-of-the-art approaches in conversion modeling. Our analysis motivates the idea of weighting the log loss with the business value of the predicted outcome. We present and analyze a new cost weighting scheme and show that significant gains in offline and online performance can be achieved.
More on http://www.kdd.org/kdd2017/
KDD2017 Conference is published on http://videolectures.net/
Видео Cost-sensitive Learning for Utility Optimization in Online Advertising Auctions канала KDD2017 video
Показать
Комментарии отсутствуют
Информация о видео
Другие видео канала
Incrementality Bidding & AttributionLearning to Make StuffProfit Maximization for Online Advertising Demand-Side PlatformA/B Testing in Networks with Adversarial MembersStacked Ensemble Models and Data Science CompetitionsCultural CreativityMentoring Session PanelMM2RTB: Bring Multimedia Metrics to Real-Time BiddingManaging Research Team PanelMatariki Tauira 2022: Rēhua by Rob MumfordPerformance comparison of dynamic prediction based on joint models and landmark analysisMatariki Tauira 2022: Jill Campbell discusses Tautoru at Matariki Tauira 2022Buy Real World Properties with CryptoMaking Rust crates compile faster.