Credit Card Fraud Prediction Using Machine Learning Model
No Thumbnail Available
Date
2024-08
Authors
Journal Title
Journal ISSN
Volume Title
Publisher
University of Essex
Abstract
The widespread adoption of credit cards has significantly increased the frequency of fraudulent activities.
This has resulted in considerable financial losses for both consumers and financial institutions. As the use
of credit cards continues to grow, the challenge of protecting transactions against unauthorized access has
become more serious than ever. This research focuses on creating a solution using machine learning to
accurately and effectively identify fraudulent credit card transactions. It addresses the issue of uneven
transaction data by employing advanced methods such as logistic regression, XGBoost, LightGBM, and a
hybrid model. The research involves thorough data preparation, model development, and careful assessment
using measures “such as accuracy, precision, recall, F1 score, and ROC AUC”. This research leverages
sophisticated machine learning techniques and tackles the specific challenges associated with imbalanced
data. The study aims to significantly enhance the detection of fraudulent transactions while reducing false
positives. The ultimate goal is to boost the security of financial systems, thus providing better protection
against fraud, and to improve trust and reliability in credit card transactions.
Description
Title: Credit Card Fraud Prediction Using Machine Learning Models
Author: Mohammed Falah S. Alanazi
Degree: Master of Science in Artificial Intelligence and its Applications
Institution: University of Essex
Award Date: 26 November 2024
Description:
The increasing use of credit cards has brought remarkable convenience to consumers and businesses but has also resulted in a rise in fraudulent activities, posing significant challenges to financial systems. This dissertation presents a comprehensive study on credit card fraud prediction through the application of advanced machine learning models.
The research investigates the effectiveness of three prominent algorithms—Logistic Regression, XGBoost, and LightGBM—and introduces a hybrid model that combines their strengths. By addressing the critical challenge of imbalanced datasets, the study employs data preprocessing techniques such as SMOTE (Synthetic Minority Over-sampling Technique) and anomaly detection using Isolation Forest to enhance model performance.
The models were rigorously evaluated using accuracy, precision, recall, F1 score, and ROC AUC metrics, demonstrating their ability to effectively detect fraudulent transactions while minimizing false positives. The findings underscore the potential of machine learning in transforming fraud detection systems, offering robust and scalable solutions for financial institutions.
This work aims to contribute to the growing body of knowledge in artificial intelligence applications for financial security, promoting innovative methods to combat fraud and enhance trust in digital financial transactions.
Keywords
Credit Card Fraud, Machine Learning, Fraud Detection, Logistic Regression, XGBoost, LightGBM, Hybrid Models, Imbalanced Datasets, SMOTE (Synthetic Minority Over-sampling Technique), Anomaly Detection, Isolation Forest, Financial Security, Artificial Intelligence Applications, Digital Transactions, Data Preprocessing