Research on CTR prediction based on stacked autoencoder

Click-through rate prediction is critical in internet advertising and affects web publisher’s profits and advertiser’s payment. In the CTR prediction, mining the interaction between features and extracting user interest are key factors affecting the prediction rate. The traditional method of obtaining features using feature extraction did not consider the sparseness of advertising data and the highly nonlinear association between features. To reduce the sparseness of data and to mine the hidden features and user interest in advertising data, a method that learns the sparse features is proposed. Our method exploits dimension reduction based on decomposition, and uses the bidirectional gated recurrent unit (Bi-GRU) to extract user interest. We utilize stacked autoencoder to portray the nonlinear associated relationship of data. The experiment shows that our method improves the effect of CTR prediction and produces economic benefits in internet advertising.

[1]  Ilya Trofimov,et al.  Using Neural Networks for Click Prediction of Sponsored Search , 2014, ArXiv.

[2]  Geoffrey E. Hinton,et al.  Deep Learning , 2015, Nature.

[3]  Tamara G. Kolda,et al.  Scalable Tensor Decompositions for Multi-aspect Data Mining , 2008, 2008 Eighth IEEE International Conference on Data Mining.

[4]  Alex Graves,et al.  Recurrent Models of Visual Attention , 2014, NIPS.

[5]  Erick Cantú-Paz,et al.  Personalized click prediction in sponsored search , 2010, WSDM '10.

[6]  Aoying Zhou,et al.  Computational Advertising: A Data-Centric Comprehensive Web Application: Computational Advertising: A Data-Centric Comprehensive Web Application , 2011 .

[7]  Yunming Ye,et al.  DeepFM: An End-to-End Wide & Deep Learning Framework for CTR Prediction , 2018, ArXiv.

[8]  Barry Smyth,et al.  Coevolutionary Recommendation Model: Mutual Learning between Ratings and Reviews , 2018, WWW.

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

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

[11]  Guigang Zhang,et al.  Deep Learning , 2016, Int. J. Semantic Comput..

[12]  Geoffrey E. Hinton,et al.  Speech recognition with deep recurrent neural networks , 2013, 2013 IEEE International Conference on Acoustics, Speech and Signal Processing.

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

[14]  Matthew Richardson,et al.  Predicting clicks: estimating the click-through rate for new ads , 2007, WWW '07.

[15]  Qiang Yang,et al.  Personalized click model through collaborative filtering , 2012, WSDM '12.

[16]  Steffen Rendle,et al.  Factorization Machines with libFM , 2012, TIST.

[17]  Tat-Seng Chua,et al.  Attentional Factorization Machines: Learning the Weight of Feature Interactions via Attention Networks , 2017, IJCAI.

[18]  Wang Jun,et al.  Product-Based Neural Networks for User Response Prediction , 2016 .

[19]  Zhou Ao.  Computational Advertising:A Data-Centric Comprehensive Web Application , 2011 .

[20]  U. Beier,et al.  Standardization, Evaluation, and Area-Under-Curve Analysis of Human and Murine Treg Suppressive Function. , 2016, Methods in molecular biology.

[21]  Chong Zhao,et al.  A New Approach for Mobile Advertising Click-Through Rate Estimation Based on Deep Belief Nets , 2017, Comput. Intell. Neurosci..

[22]  Yoshua Bengio,et al.  Learning Phrase Representations using RNN Encoder–Decoder for Statistical Machine Translation , 2014, EMNLP.

[23]  Martin Wattenberg,et al.  Ad click prediction: a view from the trenches , 2013, KDD.

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

[25]  Rohit Kumar,et al.  Predicting clicks: CTR estimation of advertisements using Logistic Regression classifier , 2015, 2015 IEEE International Advance Computing Conference (IACC).

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

[27]  Xiangnan He,et al.  Attentive Collaborative Filtering: Multimedia Recommendation with Item- and Component-Level Attention , 2017, SIGIR.

[28]  Pawel Misiorek,et al.  Tensor-Based Modeling of Temporal Features for Big Data CTR Estimation , 2017, BDAS.

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

[30]  Chih-Jen Lin,et al.  A Learning-Rate Schedule for Stochastic Gradient Methods to Matrix Factorization , 2015, PAKDD.

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

[32]  Gitta Kutyniok,et al.  A Mathematical Framework for Feature Selection from Real-World Data with Non-Linear Observations , 2016, ArXiv.

[33]  J. A. Hartigan,et al.  A k-means clustering algorithm , 1979 .

[34]  Tie-Yan Liu,et al.  Sequential Click Prediction for Sponsored Search with Recurrent Neural Networks , 2014, AAAI.

[35]  Heng-Tze Cheng,et al.  Wide & Deep Learning for Recommender Systems , 2016, DLRS@RecSys.

[36]  Geoffrey E. Hinton,et al.  Autoencoders, Minimum Description Length and Helmholtz Free Energy , 1993, NIPS.

[37]  Yoram Singer,et al.  Adaptive Subgradient Methods for Online Learning and Stochastic Optimization , 2011, J. Mach. Learn. Res..

[38]  Tat-Seng Chua,et al.  Neural Factorization Machines for Sparse Predictive Analytics , 2017, SIGIR.

[39]  Iasonas Kokkinos,et al.  DeepLab: Semantic Image Segmentation with Deep Convolutional Nets, Atrous Convolution, and Fully Connected CRFs , 2016, IEEE Transactions on Pattern Analysis and Machine Intelligence.