Credit Card Fraud Detection - Machine Learning methods

TLDR

Credit card fraud involves the loss of a card or its sensitive information, and many machine‑learning algorithms can detect such fraud. This research compares several algorithms for classifying transactions as fraud or genuine. Using the Credit Card Fraud Detection dataset, the authors applied SMOTE to address class imbalance, performed feature selection, split the data into training and test sets, and evaluated Logistic Regression, Random Forest, Naive Bayes, and Multilayer Perceptron. All algorithms achieved high accuracy for fraud detection, and the proposed model can also detect other irregularities.

Abstract

Credit card fraud refers to the physical loss of credit card or loss of sensitive credit card information. Many machine-learning algorithms can be used for detection. This research shows several algorithms that can be used for classifying transactions as fraud or genuine one. Credit Card Fraud Detection dataset was used in the research. Because the dataset was highly imbalanced, SMOTE technique was used for oversampling. Further, feature selection was performed and dataset was split into two parts, training data and test data. The algorithms used in the experiment were Logistic Regression, Random Forest, Naive Bayes and Multilayer Perceptron. Results show that each algorithm can be used for credit card fraud detection with high accuracy. Proposed model can be used for detection of other irregularities.