Research Article
Diksha Tatavat
Journal
International Journal of Digital Applications and Contemporary Research (IJDACR)
ISSN
2319-4863
Volume / Issue
Vol.14 · Issue 1
Published
August 2025
Access
Open Access
Licence
CC BY-NC-SA 4.0
Detecting credit card frauds in financial sector has become a burning issue with the increase in the volume of transactions and the frauds taking more advanced forms. Dynamic, high-dimensional, and imbalanced financial data cannot be analyzed using traditional and rule-based models, as well as statistical ones. This paper focuses on artificial neural networks (ANNs) as a way of real-time fraud detection using a nonlinear pattern recognition and deep feature learning framework. The ANN performance is compared with other models using scenario-based evaluation, such as Logistic Regression and the Support Vector machines and the Random Forests. The literature review is based on using insights of Generative AI application in the finances sphere, evolutionary optimization of deep learning parameters, synthetic image generation by GANs, and anomaly detection in the financial markets. Findings indicate that ANNs are more effective than traditional ML models in recall and fraud detection accuracy, which are some of these problems like imbalance between different classes, nonlinear behaviour and concealed fraud patterns. The study mentions the future of deep learning, neural-generated fake samples of frauds, and integrated models that involve both LLM and ANN-based anomaly detection tools.
Diksha Tatavat (2025). Neural Network-Based Credit Card Fraud Detection Using Machine Learning. International Journal of Digital Applications and Contemporary Research (IJDACR), Vol.14, Issue 1. ISSN: 2319-4863.
Full references are available in the PDF version of this paper.
Download Full Paper (PDF) →Share This Paper
Call for Submissions
IJDACR accepts submissions on a rolling basis. Authors are advised to consult the preparation guidelines and scope documentation prior to submission.
Submissions are subject to editorial screening and peer review. Submission does not guarantee acceptance.