Year: 2024
Type: article
Abstract: The global danger posed by credit card fraud to financial institutions and customers makes the development of strong fraud detection systems imperative. In this study, we suggest a novel method for detecting credit card fraud that makes use of Convolutional Neural Networks (CNNs) and synthetic data generation. Inadequate feature representations and unbalanced datasets are common problems for traditional fraud detection algorithms. We use synthetic data generation techniques to build a balanced dataset that accurately represents the intricacies of fraudulent transactions in order to overcome these difficulties.
Authors: Saurav Naik, Aarth Dahale
Institution: MIT World Peace University
Language: English
Subfield: Artificial Intelligence
Field: Computer Science
Domain: Physical Sciences
Open Access status: bronze
OpenAlex ID: W4401644894