An improved advertising CTR prediction approach based on the fuzzy deep neural network

Combining a deep neural network with fuzzy theory, this paper proposes an advertising click-through rate (CTR) prediction approach based on a fuzzy deep neural network (FDNN). In this approach, fuzzy Gaussian-Bernoulli restricted Boltzmann machine (FGBRBM) is first applied to input raw data from advertising datasets. Next, fuzzy restricted Boltzmann machine (FRBM) is used to construct the fuzzy deep belief network (FDBN) with the unsupervised method layer by layer. Finally, fuzzy logistic regression (FLR) is utilized for modeling the CTR. The experimental results show that the proposed FDNN model outperforms several baseline models in terms of both data representation capability and robustness in advertising click log datasets with noise.

[1]  Vasudeva Varma,et al.  Learning the click-through rate for rare/new ads from similar ads , 2010, SIGIR.

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

[3]  James J. Buckley,et al.  Fuzzy Probabilities : New Approach and Applications , 2005 .

[4]  Shigeru Katagiri,et al.  Confusion-Matrix-Based Kernel Logistic Regression for Imbalanced Data Classification , 2017, IEEE Transactions on Knowledge and Data Engineering.

[5]  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).

[6]  C. L. Philip Chen,et al.  Fuzzy Restricted Boltzmann Machine for the Enhancement of Deep Learning , 2015, IEEE Transactions on Fuzzy Systems.

[7]  Tianbao Yang,et al.  Improved Dropout for Shallow and Deep Learning , 2016, NIPS.

[8]  Zhou Zhen,et al.  A Method for Priorities of Triangular Fuzzy Number Complementary Judgment Matrices , 2005 .

[9]  Plamen Angelov,et al.  Advances in Computational Intelligence Systems - Contributions Presented at the 16th UK Workshop on Computational Intelligence, September 7-9, 2016, Lancaster, UK , 2017, UKCI.

[10]  Hyun-Chul Kim,et al.  Evaluation of weight sparsity regularizion schemes of deep neural networks applied to functional neuroimaging data , 2017, 2017 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP).

[11]  Chih-Jen Lin,et al.  Field-aware Factorization Machines for CTR Prediction , 2016, RecSys.

[12]  Hongtao Lu,et al.  Deep CTR Prediction in Display Advertising , 2016, ACM Multimedia.

[13]  Robert Ivor John,et al.  Type-2 Fuzzy Alpha-Cuts , 2017, IEEE Transactions on Fuzzy Systems.

[14]  Jerzy Baranowski.  Stabilisation of the second order system with a time delay controller , 2016 .

[15]  Sankaran Mahadevan,et al.  An improved method to construct basic probability assignment based on the confusion matrix for classification problem , 2016, Inf. Sci..

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

[17]  Kristin Fridgeirsdottir,et al.  Cost-Per-Click Pricing for Display Advertising , 2014, Manuf. Serv. Oper. Manag..

[18]  Xiaojie Yuan,et al.  Purchase Behavior Prediction in E-Commerce with Factorization Machines , 2016, IEICE Trans. Inf. Syst..

[19]  Zilong Jiang,et al.  Research on CTR Prediction for Contextual Advertising Based on Deep Architecture Model , 2016 .

[20]  Hui Xiong,et al.  Introduction to special section on intelligent mobile knowledge discovery and management systems , 2013, ACM Trans. Intell. Syst. Technol..

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

[22]  S. Lydersen,et al.  Clinical diagnostic accuracy of acute colonic diverticulitis in patients admitted with acute abdominal pain, a receiver operating characteristic curve analysis , 2016, International Journal of Colorectal Disease.

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

[24]  Feng Jia,et al.  An Intelligent Fault Diagnosis Method Using Unsupervised Feature Learning Towards Mechanical Big Data , 2016, IEEE Transactions on Industrial Electronics.

[25]  Thomas A. Runkler,et al.  DECADE — fast centroid approximation defuzzification for real time fuzzy control applications , 1994, SAC '94.

[26]  A. Jiménez‐Valverde.  Insights into the area under the receiver operating characteristic curve (AUC) as a discrimination measure in species distribution modelling , 2012 .

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

[28]  Yee Whye Teh,et al.  A Fast Learning Algorithm for Deep Belief Nets , 2006, Neural Computation.

[29]  Zhi-Hua Zhou,et al.  Dropout Rademacher complexity of deep neural networks , 2014, Science China Information Sciences.

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

[31]  Witold Pedrycz,et al.  An overview on the roles of fuzzy set techniques in big data processing: Trends, challenges and opportunities , 2017, Knowl. Based Syst..

[32]  Stuart E. Dreyfus,et al.  Artificial neural networks, back propagation, and the Kelley-Bryson gradient procedure , 1990 .

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

[34]  Enhong Chen,et al.  Sparse Factorization Machines for Click-through Rate Prediction , 2016, 2016 IEEE 16th International Conference on Data Mining (ICDM).

[35]  Khan A. Wahid,et al.  Automated Adaptive Brightness in Wireless Capsule Endoscopy Using Image Segmentation and Sigmoid Function , 2016, IEEE Transactions on Biomedical Circuits and Systems.

[36]  Yoshiki Uchikawa,et al.  On fuzzy modeling using fuzzy neural networks with the back-propagation algorithm , 1992, IEEE Trans. Neural Networks.

[37]  Mihir K. Chakraborty,et al.  Fuzzy relation and fuzzy function over fuzzy sets: a retrospective , 2015, Soft Comput..

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

[39]  T. Osman,et al.  Driving factors of urban sprawl in Giza governorate of the Greater Cairo Metropolitan Region using a logistic regression model , 2016 .

[40]  Douglas N Rutledge,et al.  PLS/OPLS models in metabolomics: the impact of permutation of dataset rows on the K-fold cross-validation quality parameters. , 2015, Molecular bioSystems.

[41]  Xu Ze-shui.  A Method for Priorities of Triangular Fuzzy Number Complementary Judgement Matrices , 2002 .