Functional Bid Landscape Forecasting for Display Advertising Yuchen Wang 1 Kan Ren 1 Weinan Zhang 1 Jun Wang 2 Yong Yu 1 1 Apex Data and Knowledge Management Lab Shanghai Jiao Tong University 2 University College London ECML-PKDD 2016 Yuchen Wang, Kan Ren, Weinan Zhang , Jun Wang, Yong Yu (Universities of Somewhere and Elsewhere) Functional Bid Landscape Forecasting for Display Advertising ECML-PKDD 2016 1 / 29
Outline Background 1 Real-time Bidding Bid Landscape Forecasting Challenges 2 Related Work 3 Functional Bid Landscape Forecasting 4 Tree-based Mapping Node Splitting Survival Modeling Experiments 5 Conclusion 6 Yuchen Wang, Kan Ren, Weinan Zhang , Jun Wang, Yong Yu (Universities of Somewhere and Elsewhere) Functional Bid Landscape Forecasting for Display Advertising ECML-PKDD 2016 2 / 29
Background Real-time Bidding Outline Background 1 Real-time Bidding Bid Landscape Forecasting Challenges 2 Related Work 3 Functional Bid Landscape Forecasting 4 Tree-based Mapping Node Splitting Survival Modeling Experiments 5 Conclusion 6 Yuchen Wang, Kan Ren, Weinan Zhang , Jun Wang, Yong Yu (Universities of Somewhere and Elsewhere) Functional Bid Landscape Forecasting for Display Advertising ECML-PKDD 2016 3 / 29
Background Real-time Bidding Online Advertising Goal of Computer Address the right user with the right message in the right context and at the right prices . Yuchen Wang, Kan Ren, Weinan Zhang , Jun Wang, Yong Yu (Universities of Somewhere and Elsewhere) Functional Bid Landscape Forecasting for Display Advertising ECML-PKDD 2016 4 / 29
Background Real-time Bidding Real-time Bidding (RTB) in Display Ads Scenario Yuchen Wang, Kan Ren, Weinan Zhang , Jun Wang, Yong Yu (Universities of Somewhere and Elsewhere) Functional Bid Landscape Forecasting for Display Advertising ECML-PKDD 2016 5 / 29
Background Bid Landscape Forecasting Outline Background 1 Real-time Bidding Bid Landscape Forecasting Challenges 2 Related Work 3 Functional Bid Landscape Forecasting 4 Tree-based Mapping Node Splitting Survival Modeling Experiments 5 Conclusion 6 Yuchen Wang, Kan Ren, Weinan Zhang , Jun Wang, Yong Yu (Universities of Somewhere and Elsewhere) Functional Bid Landscape Forecasting for Display Advertising ECML-PKDD 2016 6 / 29
Background Bid Landscape Forecasting Terminologies Market Price The second highest bid price proposed by all the advertisers in the auction. Yuchen Wang, Kan Ren, Weinan Zhang , Jun Wang, Yong Yu (Universities of Somewhere and Elsewhere) Functional Bid Landscape Forecasting for Display Advertising ECML-PKDD 2016 7 / 29
Background Bid Landscape Forecasting Terminologies Market Price The second highest bid price proposed by all the advertisers in the auction. Bid Landscape Forecasting To forecast the market price distribution (p.d.f.) of the specific auction. Yuchen Wang, Kan Ren, Weinan Zhang , Jun Wang, Yong Yu (Universities of Somewhere and Elsewhere) Functional Bid Landscape Forecasting for Display Advertising ECML-PKDD 2016 7 / 29
Background Bid Landscape Forecasting Bid Landscape Forecasting Example auction feature: weekday= Friday , city= New York , hour= 20 , ... Goal To forecast the market price distribution of the specific auction (impression level). market price log normal probability 0.018 0.016 log normal probability 0.014 0.012 0.010 0.008 0.006 0.004 0.002 0.000 0 50 100 150 200 250 300 market price Yuchen Wang, Kan Ren, Weinan Zhang , Jun Wang, Yong Yu (Universities of Somewhere and Elsewhere) Functional Bid Landscape Forecasting for Display Advertising ECML-PKDD 2016 8 / 29
Challenges Modeling Right Censored Data Modeling Right Censored Data Losing and Winning Yuchen Wang, Kan Ren, Weinan Zhang , Jun Wang, Yong Yu (Universities of Somewhere and Elsewhere) Functional Bid Landscape Forecasting for Display Advertising ECML-PKDD 2016 9 / 29
Challenges Modeling Right Censored Data Modeling Right Censored Data Right Censored Right Censorship As in 2 nd price auction, if you lose , you only know that the market price is higher than your bidding price, which result in right censorship. Yuchen Wang, Kan Ren, Weinan Zhang , Jun Wang, Yong Yu (Universities of Somewhere and Elsewhere) Functional Bid Landscape Forecasting for Display Advertising ECML-PKDD 2016 10 / 29
Related Work Heuristic Form Heuristic Form Log-normal Form − (ln z − µ )2 1 p z ( z ) = e , z > 0 . 2 σ 2 √ z σ 2 π Y. Cui et al. Bid landscape forecasting in online ad exchange marketplace. KDD 2011 Yuchen Wang, Kan Ren, Weinan Zhang , Jun Wang, Yong Yu (Universities of Somewhere and Elsewhere) Functional Bid Landscape Forecasting for Display Advertising ECML-PKDD 2016 11 / 29
Related Work Forecasting Forecasting Regression Model v i as the predicted winning price, v i ≈ β T x i + ǫ i , − log( φ ( w i − β T x i � minimize )) . σ i ∈ W W. Wu et al. Predicting Winning Price in Real Time Bidding with Censored Data. KDD 2015 Yuchen Wang, Kan Ren, Weinan Zhang , Jun Wang, Yong Yu (Universities of Somewhere and Elsewhere) Functional Bid Landscape Forecasting for Display Advertising ECML-PKDD 2016 12 / 29
Related Work Censorship Handling Censorship Handling Mixture Model v i = [ P ( v i < b i ) β lm + (1 − P ( v i < b i )) β clm ] T x i = β T mix x i . W. Wu et al. Predicting Winning Price in Real Time Bidding with Censored Data. KDD 2015 Yuchen Wang, Kan Ren, Weinan Zhang , Jun Wang, Yong Yu (Universities of Somewhere and Elsewhere) Functional Bid Landscape Forecasting for Display Advertising ECML-PKDD 2016 13 / 29
Functional Bid Landscape Forecasting Tree-based Mapping Outline Background 1 Real-time Bidding Bid Landscape Forecasting Challenges 2 Related Work 3 Functional Bid Landscape Forecasting 4 Tree-based Mapping Node Splitting Survival Modeling Experiments 5 Conclusion 6 Yuchen Wang, Kan Ren, Weinan Zhang , Jun Wang, Yong Yu (Universities of Somewhere and Elsewhere) Functional Bid Landscape Forecasting for Display Advertising ECML-PKDD 2016 14 / 29
Functional Bid Landscape Forecasting Tree-based Mapping Tree-based Mapping Goal Given the auction feature x , forecast the market price distribution p x ( z ). Yuchen Wang, Kan Ren, Weinan Zhang , Jun Wang, Yong Yu (Universities of Somewhere and Elsewhere) Functional Bid Landscape Forecasting for Display Advertising ECML-PKDD 2016 15 / 29
Functional Bid Landscape Forecasting Tree-based Mapping Tree-based Mapping Methodology Yuchen Wang, Kan Ren, Weinan Zhang , Jun Wang, Yong Yu (Universities of Somewhere and Elsewhere) Functional Bid Landscape Forecasting for Display Advertising ECML-PKDD 2016 16 / 29
Functional Bid Landscape Forecasting Node Splitting Outline Background 1 Real-time Bidding Bid Landscape Forecasting Challenges 2 Related Work 3 Functional Bid Landscape Forecasting 4 Tree-based Mapping Node Splitting Survival Modeling Experiments 5 Conclusion 6 Yuchen Wang, Kan Ren, Weinan Zhang , Jun Wang, Yong Yu (Universities of Somewhere and Elsewhere) Functional Bid Landscape Forecasting for Display Advertising ECML-PKDD 2016 17 / 29
Functional Bid Landscape Forecasting Node Splitting Node Splitting Yuchen Wang, Kan Ren, Weinan Zhang , Jun Wang, Yong Yu (Universities of Somewhere and Elsewhere) Functional Bid Landscape Forecasting for Display Advertising ECML-PKDD 2016 18 / 29
Functional Bid Landscape Forecasting Node Splitting Node Splitting KLD and Clustering Kullback-Leibler Divergence (KLD) A measure of the difference between two probability distributions P and Q . Yuchen Wang, Kan Ren, Weinan Zhang , Jun Wang, Yong Yu (Universities of Somewhere and Elsewhere) Functional Bid Landscape Forecasting for Display Advertising ECML-PKDD 2016 19 / 29
Functional Bid Landscape Forecasting Node Splitting Node Splitting KLD and Clustering Kullback-Leibler Divergence (KLD) A measure of the difference between two probability distributions P and Q . Node Splitting (one step) Divide all the category (including in this node) values into two sets, maximizing KLD between the resulted two sets. Yuchen Wang, Kan Ren, Weinan Zhang , Jun Wang, Yong Yu (Universities of Somewhere and Elsewhere) Functional Bid Landscape Forecasting for Display Advertising ECML-PKDD 2016 19 / 29
Functional Bid Landscape Forecasting Node Splitting Node Splitting KLD and Clustering Kullback-Leibler Divergence (KLD) A measure of the difference between two probability distributions P and Q . Node Splitting (one step) Divide all the category (including in this node) values into two sets, maximizing KLD between the resulted two sets. Algorithm Using K-Means Clustering according to KLD values. Yuchen Wang, Kan Ren, Weinan Zhang , Jun Wang, Yong Yu (Universities of Somewhere and Elsewhere) Functional Bid Landscape Forecasting for Display Advertising ECML-PKDD 2016 19 / 29
Functional Bid Landscape Forecasting Node Splitting Node Splitting KLD and Clustering Yuchen Wang, Kan Ren, Weinan Zhang , Jun Wang, Yong Yu (Universities of Somewhere and Elsewhere) Functional Bid Landscape Forecasting for Display Advertising ECML-PKDD 2016 20 / 29
Recommend
More recommend
