Credit Card Fraud Detection using Big Data Analytics: Use of PSOAANN based One-Class Classification

Banking and financial industries are facing severe challenges in the form of fraudulent transactions. Credit card fraud is one example of them. In order to detect credit card fraud, we employed one-class classification approach in big data paradigm. We implemented a hybrid architecture of Particle Swarm Optimization and Auto-Associative Neural Network for one-class classification in Spark computational framework. In this paper, we implemented parallelization of the auto-associative neural network in the hybrid architecture.

[1]  Janaina Mourão Miranda,et al.  Patient classification as an outlier detection problem: An application of the One-Class Support Vector Machine , 2011, NeuroImage.

[2]  Sasmita Panigrahi,et al.  A Hybrid Distributed Collaborative Filtering Recommender Engine Using Apache Spark , 2016, ANT/SEIT.

[3]  Aruna Tiwari,et al.  Fuzzy Based Clustering Algorithms to Handle Big Data with Implementation on Apache Spark , 2016, 2016 IEEE Second International Conference on Big Data Computing Service and Applications (BigDataService).

[4]  Ajith Abraham,et al.  Inertia Weight strategies in Particle Swarm Optimization , 2011, 2011 Third World Congress on Nature and Biologically Inspired Computing.

[5]  Michael J. Franklin,et al.  Resilient Distributed Datasets: A Fault-Tolerant Abstraction for In-Memory Cluster Computing , 2012, NSDI.

[6]  Russell C. Eberhart,et al.  A new optimizer using particle swarm theory , 1995, MHS'95. Proceedings of the Sixth International Symposium on Micro Machine and Human Science.

[7]  Scott Shenker,et al.  Spark: Cluster Computing with Working Sets , 2010, HotCloud.

[8]  M. Kramer Nonlinear principal component analysis using autoassociative neural networks , 1991 .

[9]  Sachin Shetty,et al.  SCREDENT: Scalable Real-time Anomalies Detection and Notification of Targeted Malware in Mobile Devices , 2016, ANT/SEIT.

[10]  Ameet Talwalkar,et al.  MLlib: Machine Learning in Apache Spark , 2015, J. Mach. Learn. Res..

[11]  Scott Shenker,et al.  Fast and Interactive Analytics over Hadoop Data with Spark , 2012, login Usenix Mag..

[12]  Jason J. Jung,et al.  Social big data: Recent achievements and new challenges , 2015, Information Fusion.

[13]  Tim Kraska,et al.  MLbase: A Distributed Machine-learning System , 2013, CIDR.

[14]  Vadlamani Ravi,et al.  Extreme Learning Machine , 2013 .

[15]  Vadlamani Ravi,et al.  Phishing Detection Using PSOAANN Based One-Class Classifier , 2013, 2013 6th International Conference on Emerging Trends in Engineering and Technology.

[16]  Robert P. W. Duin,et al.  Uniform Object Generation for Optimizing One-class Classifiers , 2002, J. Mach. Learn. Res..

[17]  Lee Sael,et al.  Procedia Computer Science , 2015 .

[18]  Sanjay Ghemawat,et al.  MapReduce: Simplified Data Processing on Large Clusters , 2004, OSDI.

[19]  Vadlamani Ravi,et al.  A particle swarm optimization-threshold accepting hybrid algorithm for unconstrained optimization , 2013 .

[20]  Vadlamani Ravi,et al.  Particle Swarm Optimization Trained Auto Associative Neural Networks Used as Single Class Classifier , 2012, SEMCCO.

[21]  Tim Kraska,et al.  MLI: An API for Distributed Machine Learning , 2013, 2013 IEEE 13th International Conference on Data Mining.

[22]  Vadlamani Ravi,et al.  Privacy preserving data mining using particle swarm optimisation trained auto-associative neural network: an application to bankruptcy prediction in banks , 2012, Int. J. Data Min. Model. Manag..