Customer retention and credit risk analysis using ANN, SVM and DNN
by Nagaraj V. Dharwadkar; Priyanka S. Patil
International Journal of Society Systems Science (IJSSS), Vol. 10, No. 4, 2018

Abstract: Nowadays, the banking sector are facing various challenges such as customer retention, fraud detection, risk management and customer segmentation. It can be possible to find solutions to these problems with the help of data analytics and machine learning (ML). In this paper, we have proposed a model which provides the solution to problems of the banking sector for customer retention and credit risk analysis. We used supervised learning techniques namely artificial neural network (ANN), support vector machine (SVM) and deep neural network (DNN) to analyse bank customer data. In order to analyse the algorithms we have used German credit dataset to evaluate the customer retention and credit risk. The experimental result shows that the using ANN, SVM and DNN algorithms, we could able to to reach recognition accuracy of 98%, 92% and 97% respectively for bank customer data and 72%, 72% and 76% for German credit dataset. The proposed method provides an efficient solution for retention and credit risk analysis of bank customers, which improves the profit of the banks by retaining the customers.

Online publication date: Thu, 11-Oct-2018

The full text of this article is only available to individual subscribers or to users at subscribing institutions.

 
Existing subscribers:
Go to Inderscience Online Journals to access the Full Text of this article.

Pay per view:
If you are not a subscriber and you just want to read the full contents of this article, buy online access here.

Complimentary Subscribers, Editors or Members of the Editorial Board of the International Journal of Society Systems Science (IJSSS):
Login with your Inderscience username and password:

Username:        Password:          Forgotten your password?

Want to subscribe?
A subscription gives you complete access to all articles in the current issue, as well as to all articles in the previous three years (where applicable). See our Orders page to subscribe.

If you still need assistance, please email subs@inderscience.com