Multi-objective Optimization for Guaranteed Delivery in Video Service Platform

Guaranteed-Delivery (GD) is one of the important display strategies for the IP videos in video service platform. Different from the traditional recommendation strategy, GD requires the delivery system to guarantee the exposure amount (also called impressions in some works) for the content, where the amount generally comes from the purchase contract or business consideration of the platform. In this paper, we study the problem of how to maximize certain gains, such as video view (VV) or fairness of different contents (CTR variations between contents) under the GD constraints. We formulate such a problem as a constrained nonlinear programming problem, in which the objectives are to maximize the total VVs of contents and the exposure fairness between contents. In order to capture the trends of VV versus the impression number (page views, PV) for each video content, we propose a parameterized ordinary differential equation (ODE) model, and the parameters of the ODE are fitted by the video historical PV and CLICK datas. To solve the constrained nonlinear programming, we use genetic algorithm (GA) with a specific design of coding scheme considering the ODE constraints. The empirical study based on real-world data and online test on Youku.com verifies the effectiveness and superiority of our approach compared with the state of the art in the industry practice.

[1]  Jun Wang,et al.  Deep Learning over Multi-field Categorical Data - - A Case Study on User Response Prediction , 2016, ECIR.

[2]  H. Brendan McMahan,et al.  Follow-the-Regularized-Leader and Mirror Descent: Equivalence Theorems and L1 Regularization , 2011, AISTATS.

[3]  Olivier Chapelle,et al.  Offline Evaluation of Response Prediction in Online Advertising Auctions , 2015, WWW.

[4]  Sergei Vassilvitskii,et al.  SHALE: an efficient algorithm for allocation of guaranteed display advertising , 2012, KDD.

[5]  Joaquin Quiñonero Candela,et al.  Web-Scale Bayesian Click-Through rate Prediction for Sponsored Search Advertising in Microsoft's Bing Search Engine , 2010, ICML.

[6]  Xuerui Wang,et al.  Click-Through Rate Estimation for Rare Events in Online Advertising , 2011 .

[7]  Heinz Mühlenbein,et al.  Evolution algorithms in combinatorial optimization , 1988, Parallel Comput..

[8]  A. Kimms,et al.  Revenue management for broadcasting commercials: the channel's problem of selecting and scheduling the advertisements to be aired , 2007 .

[9]  Feng Yu,et al.  A Convolutional Click Prediction Model , 2015, CIKM.

[10]  John Turner,et al.  The Planning of Guaranteed Targeted Display Advertising , 2012, Oper. Res..

[11]  Wentong Li,et al.  Estimating conversion rate in display advertising from past erformance data , 2012, KDD.

[12]  Olivier Chapelle,et al.  Modeling delayed feedback in display advertising , 2014, KDD.

[13]  Ferenc Hartung,et al.  Chapter 5 Functional Differential Equations with State-Dependent Delays: Theory and Applications , 2006 .

[14]  Jun Wang,et al.  Product-Based Neural Networks for User Response Prediction , 2016, 2016 IEEE 16th International Conference on Data Mining (ICDM).

[15]  Srinivas Bollapragada,et al.  Special Issue: Franz Edelman Award for Achievement in Operations Research and the Management Sciences: NBC's Optimization Systems Increase Revenues and Productivity , 2002, Interfaces.

[16]  Joaquin Quiñonero Candela,et al.  Practical Lessons from Predicting Clicks on Ads at Facebook , 2014, ADKDD'14.

[17]  Suman Mallik,et al.  Scheduling Commercial Videotapes in Broadcast Television , 2004, Oper. Res..

[18]  Anh-Phuong Ta,et al.  Factorization machines with follow-the-regularized-leader for CTR prediction in display advertising , 2015, 2015 IEEE International Conference on Big Data (Big Data).

[19]  A. Mihiotis,et al.  A mathematical programming study of advertising allocation problem , 2004, Appl. Math. Comput..

[20]  Rómer Rosales,et al.  Simple and Scalable Response Prediction for Display Advertising , 2014, ACM Trans. Intell. Syst. Technol..

[21]  Yunming Ye,et al.  DeepFM: A Factorization-Machine based Neural Network for CTR Prediction , 2017, IJCAI.

[22]  Kai Liu,et al.  Learning Piece-wise Linear Models from Large Scale Data for Ad Click Prediction , 2017, ArXiv.

[23]  Fernando A. C. C. Fontes,et al.  A Decision Support System for Planning Promotion Time Slots , 2007, OR.

[24]  Flavian Vasile,et al.  Cost-sensitive Learning for Bidding in Online Advertising Auctions , 2016, ArXiv.

[25]  David Maxwell Chickering,et al.  Targeted Advertising on the Web with Inventory Management , 2003, Interfaces.

[26]  Nitasha Soni,et al.  Study of Various Crossover Operators in Genetic Algorithms , 2014 .

[27]  Gila E. Fruchter,et al.  Dynamic promotional budgeting and media allocation , 1998, Eur. J. Oper. Res..

[28]  Chengjie Sun,et al.  Predicting ad click-through rates via feature-based fully coupled interaction tensor factorization , 2016, Electron. Commer. Res. Appl..

[29]  Guorui Zhou,et al.  Deep Interest Network for Click-Through Rate Prediction , 2017, KDD.

[30]  Srinivas Bollapragada,et al.  Scheduling Commercials on Broadcast Television , 2004, Oper. Res..

[31]  David Lo,et al.  Predicting response in mobile advertising with hierarchical importance-aware factorization machine , 2014, WSDM.