Credit Card Fraud Detection

The Problem of Financial fraud is growing with far consequences in the financial industry and while many techniques have been discovered. Data mining has been applied successfully to automate analysis of huge volumes of complex data in financing the databases. For the detection of credit card fraud in online transactions, data mining has played a salient role in it. Fraud detection in credit card is a problem in field of data mining, It has becomes a challenging due to two major reasons–first, the profiles of normal and fraudulent behaviours change frequently and secondly due to reason that credit card fraud data sets are highly skewed. The paper digs-in and checks the performance of Decision tree, Random Forest, SVM and logistic regression on highly skewed credit card fraud data. Dataset of credit card transactions is sourced from European cardholders containing 284,786 transactions. These techniques are applied on the raw and pre-processed data. The performance of the above techniques is evaluated based on its accuracy, sensitivity, specificity and precision. And then the paper discusses about how to detect the fraud using Random Forest.