Applications of Data Mining Techniques for Fraud Detection in Credit-Debit Card Transactions |
Author(s): |
Mrs. Poonam M. Deshpande , Atharva College of Engineering, Mumbai University,Mumbai, India; Prof. Abul Hasan Siddiqi, School of Basic Sciences & Research, Sharda University, Greater Noida, Uttar Pradesh 201306, India; Dr. Khursheed Alam, School of Basic Sciences & Research, Sharda University, Greater Noida, Uttar Pradesh 201306, India; Mr. Khinal Parmar, Mukesh Patel School of Technology Management & Engineering, Vile Parle(W), Mumbai-400056, India |
Keywords: |
Data Mining, Credit Card Fraud, Peer Group Analysis, Pattern discovery, Behavioral Data, Neural Network |
Abstract |
Although the term FRAUD has varied definition and numerous fields to perpetrate, the major setback due to fraud is in the Credit/Debit Card Not Present (CNP) transaction like internet purchase, mail transactions (MT), telephonic transactions (TT) etc. The card fraud losses are in Billions of dollars and on the rise. The fraudsters always find novel ways to commit frauds and they know how to go around the system. Most of the times the fraud detection is done after the fraud are already committed and many of the frauds go unnoticed. Therefore credit card fraud detection methods need constant innovation [1] and all the financial institutions are required to have some fraud detection models or techniques in place to deal with such a scenario. Data Mining is basically a tool for pattern discovery, outlier or anomaly detection. It works well in detecting different types of frauds. This paper takes a review of various fraud detection techniques based on Data Mining like Neural Network, Support Vector Machines, K-nearest Neighbor, Artificial Immune System, Peer group analysis [2] etc.. We also give suggestions for a new technique which can be implemented and which will seize the essence of the existing techniques and may be combine few of them to give superior fraud detection tool. |
Other Details |
Paper ID: NCTAAP082 Published in: Conference 4 : NCTAA 2016 Publication Date: 29/01/2016 Page(s): 339-345 |
Article Preview |
Download Article |
|