| Advances in Big Data Fraud Detection: A Comprehensive Literature Review |
| Paper ID : 1096-ISCBAS |
| Authors |
|
Gaber elsayed Abutaleb *1, Abdallah adel Alhabashy2, Berihan M elemary3, Kamal El-Dahshan4 1Assistant lecturer, Mathematics Department, Faculty of Science, Al-Azhar University, Cairo, Egypt 2Associate Professor of Computer Science, Mathematics Department, Faculty of Science, Al-Azhar University, Cairo, Egypt 3Associate Professor of Statistics Department of Applied, Mathematical and Actuarial Statistics, Damietta University, Egypt 4Professor in Computer science |
| Abstract |
| The proliferation of data in recent times has created a challenge in detecting fraud. Fraudulent activities occur in various sectors such as banking, web networks, health insurance, telecommunications, among others. Consequently, there is a growing need for big data technologies such as Hadoop, Spark, Storm, and HBase to detect and analyze data fraud in real time. Detecting fraud involves analyzing data and creating machine learning models or traditional rules to identify abnormal activities as they occur. This paper presents a comprehensive literature review of big data tools used in detecting and preventing fraud. The review includes an explanation of the solutions offered, the work environments used, and the machine learning algorithms and traditional rules utilized. By the end of this review, organizations and companies will be equipped with the latest information on big data technologies and solutions that can be utilized in real-time fraud detection and prevention. |
| Keywords |
| Fraud Detection, Big Data, Machine Learning, Real Time Fraud, Apache Spark. |
| Status: Abstract Accepted (Oral Presentation) |