Data Mining for Fraud Detection

In the contemporary era, most of the operations in various domains take place through a transparent digital platform. However, there have been instances of fraudulent behavior and transactions leading to loss to individuals or entities. In this context, there is a need for technology-enhanced approaches to detect different kinds of fraud in sectors like banking, insurance, healthcare and e-commerce, to mention a few, for sustainable digitalization. With technological innovations such as the Internet of Things (IoT) and cloud computing, unprecedented applications emerged. This has also brought increased fraud instances. At the same time, Artificial Intelligence (AI) along with data mining, machine learning and deep learning is found to solve problems in the real world. Therefore, it is essential to ascertain the present state of the art in fraud detection. Towards this end, this paper focuses on a systematic review of existing data mining or AI methods used for fraud detection in different domains. The insights of this paper can trigger further research in the area of automatic fraud detection.