<![CDATA[This study aims to apply a machine learning approach in detecting fraud in digital payment transactions in the Paper.id platform. The study was conducted using the Research and Development (R&D) method with the Cross-Industry Standard Process for Data Mining (CRISP DM) development model, which consists of six main stages, namely business understanding, data understanding, data preparation, modeling, evaluation, and implementation. The analysis process involves data exploration, feature engineering, and the application of anomaly detection techniques and network analysis. The results of the study show that the application of the machine learning approach is significantly able to identify suspicious transaction patterns such as collusion between users, misuse of promotions, and other unusual transactions. The implementation of this system is expected to improve the accuracy of fraud detection, efficiency of transaction data processing, and strengthen data security and user trust in the Paper.id platform.]]>
Copyrights © 2025
