Application of Big Data Analytics and Pattern Recognition Aggregated With Random Forest for Detecting Fraudulent Credit Card Transactions (CCFD-BPRRF)
B.J.Jaidhan1, B. Divya Madhuri2, K. Pushpa3, B.V.S Lakshmi Devi4, Shanmuk Srinivas A5
1Dr B J Jaidhan, Associate Professor, Department of CSE, GITAM University, Visakhapatnam (Andhra Pradesh), India.
2Shanmuk Srinivas Amiripalli, Assistant Professor, Department of CSE, GITAM University, Visakhapatnam (Andhra Pradesh), India
3B. Divya Madhuri: Gandhi Institute of Technology and Management, University Visakhapatnam, (Andhra Pradesh), India.
4B.V.S.Lakshmi Devi: Gandhi Institute of Technology and Management, University. Visakhapatnam, (Andhra Pradesh), India.
5K. Pushpa, Gandhi Institute of Technology and Management, University. Visakhapatnam, (Andhra Pradesh), India.
Manuscript received on 23 March 2019 | Revised Manuscript received on 30 March 2019 | Manuscript published on 30 March 2019 | PP: 1082-1087 | Volume-7 Issue-6, March 2019 | Retrieval Number: F2427037619/19©BEIESP
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: People today tend to make multiple transactions every day. It has been observed that around 150 million transactions are being carried out every 24 hours. There are several modes through which these transactions can be accomplished, but amongst them, credit-based transactions stand ahead. Using credit system for negotiations is worthwhile for both the users and the credit providers. But with the advent of newer methodologies, illicit usage of the credit system has been growing. This situation seems like a stumbling block for both the users and the credit providers. In this pursuit, Big Data provides better and utilitarian methods and algorithms to overcome this snag. Big Data in this context helps in building an analytical model that can be integrated with Hadoop for storage and is feasible to implement pattern recognition algorithms that are aided by few machine learning algorithms to predict fraudulent patterns. This paper reflects that our proposed model comes withhigher accuracy rates when compared to the other existing decision making models.
Keywords: Big Data, Credit Card Fraud,Classification, Machine Learning Algorithms, Pattern Recognition, Random Forests, Supervised Learning
Scope of the Article: Big Data Analytics Application Systems