Credit Card Fraud Detection Using Lightgbm Machine Learning Algorithm

Credit card fraud has become a significant concern for financial institutions and cardholders worldwide. Traditional rule-based fraud detection systems are limited in their ability to adapt to evolving fraud patterns. In recent years, machine learning algorithms have shown promising results in detecting fraudulent transactions by analysing large volumes of transactional data. In this paper we aim to develop a credit card fraud detection system using machine learning algorithms. The proposed system utilizes historical transactional data, including features such as transaction amount, merchant category code, time of transaction, and cardholder information, to train a model capable of identifying fraudulent transactions. This paper follows a supervised learning approach, where a dataset consisting of labelled transactions (fraudulent and non-fraudulent) is used to train the machine learning model. Various algorithms such as logistic regression, random forest, and Light GBM are evaluated to determine the most effective approach for fraud detection.