A Hybrid Method for Credit Card Fraud Detection Using Machine Learning Algorithm
Ramyashree. K1, Janaki K2, Keerthana. S3, B.V. Harshitha4, Harshitha. Y.V5
1Ramyashree. K, Department of Computer Science and Engineering, Rajarajeswari College of Engineering, Bengaluru (Karnataka), India.
2Janaki K, Department of Computer Science and Engineering, Rajarajeswari College of Engineering, Bengaluru (Karnataka), India.
3Keerthana. S, Department of Computer Science and Engineering, Rajarajeswari College of Engineering, Bengaluru (Karnataka), India.
4B.V. Harshitha, Department of Computer Science and Engineering, Rajarajeswari College of Engineering, Bengaluru (Karnataka), India.
5Harshitha. Y.V, Department of Computer Science and Engineering, Rajarajeswari College of Engineering, Bengaluru (Karnataka), India.
Manuscript received on 24 April 2019 | Revised Manuscript received on 06 May 2019 | Manuscript Published on 17 May 2019 | PP: 235-239 | Volume-7 Issue-6S4 April 2019 | Retrieval Number: F10440476S419/2019©BEIESP
Open Access | Editorial and Publishing 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: The credit card fraud is mostly come in financial services. The credit card fraud is generated huge number of problems in every year. Lack of research on this credit card problem and submits the real-world credit card fraud analyzes, that is issues. In this paper is introduced best data mining algorithm called “machine learning algorithm”, which is utilized to recognize the credit card fraud, so initially use this algorithm and it is one of the standard model. Then, secondly apply the hybrid methods namely, “AdaBoost and majority vote method”. Use this model efficacy, which is evaluated, and then use the credit card data set it is publicly available one. The financial institution included true world data set, so it is taking and analyzed. In this robustness algorithm additionally evaluate the noise added data samples. This concept is used in experiment and then produce the result positively indicate the hybrid method, that is majority voting, it provides good accuracy rates in credit card fraud detection.
Keywords: Machine Learning, AdaBoost, Majority Voting.
Scope of the Article: Machine Learning