ATM CARD Fraud Detection Using Machine Learning

Financial fraud is an ever-growing menace with far consequences in the financial industry. Data mining had played an imperative role in the detection of ATM card fraud in online transactions. ATM card fraud detection, which is a data mining problem, becomes challenging due to two major reasons - first, the profiles of normal and fraudulent behaviors change constantly and secondly, ATM card fraud datasets are highly skewed. The performance of fraud detection in ATM card transactions are greatly affected by the sampling approach on the dataset, selection of variables and detection technique(s) used. This project investigates the performance of nave bayes, k-nearest neighbor and logistic regression on highly skewed ATM card fraud data. We build and present a machine learning model to analyze & predict fraudulent transactions. The work is implemented in R, which is a programming language for statistical computing and graphics.