A Unified Analysis of Bank Customer using Machine Learning
R. Veeramani1, P. B. Pavani Reddy2, Nikhil Raj3, Mehul Jain4
1R.Veeramani, Assistant professor of Information Technology in SRM IST, Chennai, Tamil Nadu, India.
2P.B. Pavani Reddy, Department of Information Technology, SRM IST, Chennai, Tamil Nadu, India.
3Nikhil Raj, Department of Information Technology, SRM IST, Chennai, Tamil Nadu, India.
4Mehul Jain, Department of Information Technology, SRM IST, Chennai, Tamil Nadu, India.
Manuscript received on March 15, 2020. | Revised Manuscript received on March 24, 2020. | Manuscript published on March 30, 2020. | PP: 4026-4029 | Volume-8 Issue-6, March 2020. | Retrieval Number: F9369038620/2020©BEIESP | DOI: 10.35940/ijrte.F9369.038620
Open Access | Ethics and Policies | Cite | Mendeley
© 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: In order to discover information, virtual data evaluation involves trendy computer tools and display. The use of various digital research methodologies has become quite frequent throughout society. The aim of this proposed model is to provide a new vision of customer relationship administration through visual representation and interactive techniques. Special mentions of the investigation include that consumers have a better change on consumer truthfulness in the banking sector, specifically with the expenses towards a better direction, the bond between them becomes much firmer. Lastly, comments are presented on how to make the consumer satisfied and increase their trust. They are consistently hunting for new techniques to improve their business profits like, correct commodity marketing to best consumers, accurate use of own channels, visitation on a low level to bank branches for everyday money withdrawals and etc. A unified analysis of bank customer’s helps to identify the person’s judgment and decides whom to distribute the services of bank and how much credits can be offered up to a limit. It also helps the bank issuer’s understand profile of their consumers. The model uses different algorithms (KNN, Logistic Regression XGB Classifier, Decision tree and MLP classifier) to train and test the data and then analyses the best algorithm to perform the task. As customer profiling in a bank is a highly requested service for such task, a unified analysis of the same consumer segmentation is specially customized for money minting industry.
Keywords: Credit limit, Customer profiling, Machine Learning, Segmentation.
Scope of the Article: Machine Learning.