INVESTIGATING THE EFFECTIVENESS OF UNSUPERVISED MACHINE LEARNING ALGORITHMS FOR CREDIT CARD FRAUD DETECTION

Abstract:

Credit card fraud has become a significant concern in the financial industry, resulting in substantial financial losses for individuals and businesses worldwide. Traditional rule-based fraud detection systems often struggle to keep up with the evolving techniques of fraudsters. As a result, there is a growing need for more advanced and adaptive fraud detection methods.

In recent years, unsupervised machine learning algorithms have emerged as a promising approach for credit card fraud detection. Unlike supervised learning methods, unsupervised algorithms do not require labeled training data, making them well-suited for detecting unknown and emerging fraud patterns. This study aims to investigate the effectiveness of unsupervised machine learning algorithms for credit card fraud detection.

The research methodology involves collecting a large-scale dataset of credit card transactions, including both legitimate and fraudulent transactions. Various unsupervised machine learning algorithms, such as clustering and anomaly detection techniques, will be implemented and evaluated. The performance of these algorithms will be assessed based on their ability to accurately identify fraudulent transactions while minimizing false positives.

The evaluation metrics used in this study will include precision, recall, F1-score, and area under the receiver operating characteristic curve (AUC-ROC). Additionally, the computational efficiency and scalability of the algorithms will be considered to assess their practical viability for real-time fraud detection systems.

The results of this study will provide insights into the effectiveness of unsupervised machine learning algorithms for credit card fraud detection. It will contribute to the existing body of knowledge by identifying the most promising algorithms and techniques for detecting fraudulent transactions. The findings will also inform the development of more robust and adaptive fraud detection systems that can effectively detect and mitigate credit card fraud in real-time.

Keywords: credit card fraud detection, unsupervised machine learning, clustering, anomaly detection, evaluation metrics, computational efficiency.

INVESTIGATING THE EFFECTIVENESS OF UNSUPERVISED MACHINE LEARNING ALGORITHMS FOR CREDIT CARD FRAUD DETECTION, GET MORE MASTERS COMPUTER SCIENCE

Sharing is caring!