Multi-Level Credit Card Fraud Detection
V. Sobanadevi1, G. Ravi2
1V. Sobanadevi, Research Scholar, Department of Computer Science, Jamal Mohamed College, Trichy, Tamilnadu, India.
2G. Ravi, Associate Professor and Head, Department of Computer Science, Jamal Mohamed College, Trichy, Tamilnadu, India.
Manuscript received on November 20, 2019. | Revised Manuscript received on November 28, 2019. | Manuscript published on 30 November, 2019. | PP: 7288-7292 | Volume-8 Issue-4, November 2019. | Retrieval Number: D5287118419/2019©BEIESP | DOI: 10.35940/ijrte.D5287.118419
Open Access | Ethics and Policies | Cite | Mendeley | Indexing and Abstracting
© The Authors. Blue Eyes Intelligence Engineering and Sciences Publication (BEIESP). This is an open access article under the CC-BY-NC-ND license (http://creativecommons.org/licenses/by-nc-nd/4.0/)
Abstract: Fraud detection in credit card transactions is one of the major requirements of the current business scenario due to the huge amount of losses associated with the domain. This work presents a multi-level model that can provide highly effective fraud detection in credit card transactions. The model is based on the amount for which the transaction is committed. The proposed MLFD model identifies the nature of the transaction and depending on the significance level of the transaction, the appropriate learning model is selected. Experiments were performed with the standard benchmark data and comparisons were performed with existing model in literature. Results shows that the proposed model exhibits high performance compared to the existing model.
Keywords: Credit Card Fraud Detection, Decision Tree, Multi-Level Modelling , Naïve Bayes, Random Forest.
Scope of the Article: FPGAs.