Retention Rate of Customers in Banks using Neural Networks
T. H. Feiroz Khan1, Shrushti Mhaske2, Sonal Yeshwantrao3, Ayush Kumar4
1Mr.T.H. Feiroz Khan, Computer Science and Engineering, SRM Institute of Science and Technology, Chennai, India.
2Shrushti Mhaske, Computer Science and Engineering, SRM Institute of Science and Technology, Chennai, India.
3Sonal Yeshwantrao, Computer Science and Engineering, SRM Institute of Science and Technology, Chennai, India.
4Ayush Kumar, Computer Science and Engineering, SRM Institute of Science and Technology, Chennai, India.
Manuscript received on September 23, 2019. | Revised Manuscript received on October 15, 2019. | Manuscript published on October 30, 2019. | PP: 4883-4885 | Volume-9 Issue-1, October 2019 | Retrieval Number: A1932109119/2019©BEIESP | DOI: 10.35940/ijeat.A1932.109119
Open Access | Ethics and Policies | Cite | Mendeley
Â© 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: Customer retention is the process of retaining the customers after a particular period of time. Profitability of a product depends upon the retention of the customer. In the earlier systems a lot of money, time and resources were spent on advertising by banks. Banks approached call centres to try convince the customers in buying new policies. This didn’t really work since most of it was directed towards untargeted customers. This same problem of customer retention is studied and a competent solution is found. This system consists of analysed data of a number of customers in numerous fields and checks the retaining rate of every customer. Use of a neural network is advocated to check past conditions of services provided to a customer by the banks and a common retainability index is produced which predicts the retention rate of the new customers.
Keywords: Neural Networks, Prediction, Machine learning, Accuracy, Data analysis, Linear regression, Dataset, Training, Retention Rate.