Fraud Detection on Bank Payments Using Machine Learning
Pinku Ranjan, Kammari Santhosh, A. Arun Kumar, Somesh Kumar
Abstract
This paper consists of fraud detection and measures to automate it fully. For every bank, it has become essential for Fraud detection. Fraud is rising significantly, which ends in many damages for the banks. Transactions create unique challenges for fraud exposure due to the lack of short-term processing. The foremost task is a feasibility study of chosen fraud detection methods. With the help of models, these transactions are to be tested individually and further proceeded. We first define a detection task: attributes of the dataset, the metric choice, and any techniques to control such unbalanced datasets. This leads to the fact that the underlying pattern generating the dataset results: For example, cardholders may improve their purchasing habits over periods, and fraudsters may change their tactics. Later, we highlighted several methods used to obtain the sequential features of credit card transactions.