DATA MINING FOR ONLINE FRAUD DETECTION

The project entitled “Data Mining for Online Fraud Detection” clearly proves the capability of using an array of innovative data mining technology and machine learning algorithms in detecting any sort of fraudulent transaction in an online payment system. The increasing popularity of digital payment services and e-commerce sites has resulted in an alarming rise in the need for scam uncovering in economic institutions. The proposed system was designed to acquire preprocess and analyze transaction algorithms to determine true transactions and fraudulent transactions effectively. Various testing phases appropriated dwelling during the execution of the proposed system to make it work efficiently. The experiment demonstrated that the proposed system is capable of detecting unusual transactions raising alarms and helping administrators make actions on time. This project has an accuracy of 88% It plays an important part in improving the refuge of online transactions by intelligent study of the data. It contributes to ensuring the stability of trust between the user and the company and reducing financial losses. Overall the proposed fraud detection approach offers a reliable solution to online fraud.

[1] Bolton, R. J., & Hand, D. J., “Statistical fraud detection: A review,” Statistical Science, 2002.   [2] Bhattacharyya, S., Jha, S., Tharakunnel, K., & Westland, J. C., “Data mining for credit card fraud: A comparative study,” Decision Support Systems, 50(3), 2011.   [3] Phua, C., Lee, V., Smith, K., & Gayler, R., “A comprehensive survey of data mining-based fraud detection research,” Artificial Intelligence Review, 34(1), 2010.   [4]Yang, Q., Liu, Y., Chen, T., & Tong, Y., “Federated machine learning: Concept and applications,” ACM Transactions on Intelligent Systems and Technology, 2019.   [5] Chen, T., & Guestrin, C., “XGBoost: A scalable tree boosting system,” KDD Conference, 2016.   [6] Dal Pozzolo, A., Boracchi, G., Caelen, O., Alippi, C., & Bontempi, G., “Credit card fraud detection: A realistic modeling and a novel learning strategy,” 2018.