Fintech related machine learning : credit risk analysis using machine learning models

• Main Author: Ng, Zaphyr Wee Hau
• Other Authors: Althea Liang
• Format: Final Year Project
• Language: English
• Published: Nanyang Technological University 2021
• Subjects: Engineering::Computer science and engineering::Computing methodologies::Artificial intelligence
• Online Access: https://hdl.handle.net/10356/153261
• Institution: Nanyang Technological University

Credit card payments have grown more common in recent years to make payments quickly and without regard to class. We may pay the money immediately from our bank account via the internet. Even though it is a simple payment method, it has the drawback of being prone to fraud. The term "Intruder" refers to an unauthorized individual who gains access to another person's banking information. These attackers can get access to certain illegal transactions as well. We need some effective measures in place to prevent this from happening. This article will compare the accuracy of three distinct classification methods (Logistic Regression, Random Forest, K-Nearest Neighbour and Decision tree) for fraud detection. The analysis was done using Python Software. The dataset was downloaded from the Kaggle website. A comparison between the four different models was made based on the accuracy of the test and train dataset and the accuracy of the confusion matrix. The different aspects showed that the random forest model was the most accurate to predict credit card fraud detection.