Analysis of fraud detection in credit card transactions using machine learning approach

Abdullah, Nur Fajrina (2024) Analysis of fraud detection in credit card transactions using machine learning approach. Project Report. Melaka, Malaysia, Universiti Teknikal Malaysia Melaka. (Submitted)

Text (Full Text) Analysis of fraud detection in credit card transactions using machine learning approach.pdf - Submitted Version Download (1MB)

Abstract

Machine learning is a field of artificial intelligence that enables computers to learn from and make decisions based on data. This research aims to optimize machine learning algorithms to address the growing issue of fraud in financial transactions and enhance the accuracy of fraud detection in credit card transactions. Conventional techniques often have a high false-negative rate because they struggle to keep up with evolving fraud practices and unbalanced datasets. This project utilizes a large credit card dataset from Kaggle and applies advanced machine learning methods, including Support Vector Machine, Logistic Regression, Random Forest, Decision Trees, and Neural Networks. Optimization techniques such as the Cuckoo Search Algorithm, Grasshopper Optimization Algorithm, and Genetic algorithms will be employed to enhance these models. The project aims to reduce false negatives, address data imbalance, and identify the most effective algorithm for fraud detection. The anticipated outcomes include improved fraud detection techniques and recommendations for the best performing algorithms, contributing to increased security in the financial system.

Actions (login required)

View Item