Fraudulent Data Detection of Credit Card by Using Random Forest Method to Calculate ROC and Confusion Matrix
Credit card fraud defaults in trillions of dollars online merchants. Researchers have more and more complex methods of detecting fraud using algorithms for machine learning, but there are rare reports of hands-on implementations. We describe the implementation of an extortion discovery framework in a huge e-tail retailer. The paper looks at the combination of manual and robotized classification and offers experiences into the whole handle of advancement. The paper can thus support the development and implementation of data mining tools to detect fraud or similar problems. The project helped improve their manual review process by providing not only an automatic system, but also an overview of fraud analysts, leading to overall superior performance. This project uses the Pit tool to create the required GUI. The Peruvian tool is used for automatic coding generation. This project consists of three modules: the frontend module is used to create the necessary GUI screens for the project. Payments are continuously monitored by the monitoring module.
Keywords: CVV, time distribution, information processing, arbitrary forests, GUI (graphical user interface)
Cite this Article A. Viswanathan, Sara Chandana, S. Kavya, T. Siddharth Reddy. Fraudulent Data Detection of Credit Card by using Random Forest Method to Calculate ROC and Confusion Matrix. Journal of Advanced Database Management & Systems. 2020; 7(1): 15–22p.
- There are currently no refbacks.
This site has been shifted to https://stmcomputers.stmjournals.com/