Reference Hub2
A Collaborative Mining-Based Decision Support Model for Granting Personal Loans in the Banking Sector

A Collaborative Mining-Based Decision Support Model for Granting Personal Loans in the Banking Sector

Amira M. Idrees, Ayman E. Khedr
Copyright: © 2022 |Volume: 14 |Issue: 1 |Pages: 23
ISSN: 1941-627X|EISSN: 1941-6288|EISBN13: 9781683180777|DOI: 10.4018/IJESMA.296573
Cite Article Cite Article

MLA

Idrees, Amira M., and Ayman E. Khedr. "A Collaborative Mining-Based Decision Support Model for Granting Personal Loans in the Banking Sector." IJESMA vol.14, no.1 2022: pp.1-23. http://doi.org/10.4018/IJESMA.296573

APA

Idrees, A. M. & Khedr, A. E. (2022). A Collaborative Mining-Based Decision Support Model for Granting Personal Loans in the Banking Sector. International Journal of E-Services and Mobile Applications (IJESMA), 14(1), 1-23. http://doi.org/10.4018/IJESMA.296573

Chicago

Idrees, Amira M., and Ayman E. Khedr. "A Collaborative Mining-Based Decision Support Model for Granting Personal Loans in the Banking Sector," International Journal of E-Services and Mobile Applications (IJESMA) 14, no.1: 1-23. http://doi.org/10.4018/IJESMA.296573

Export Reference

Mendeley
Favorite Full-Issue Download

Abstract

One main potential objective for financial corporations is to retain long-term customers. Configuring customer knowledge is no doubt mandatory to lower the risk level. Loans and credit cards granting are two services that are offered by the banking corporations which can be categorized as high-risk services. Therefore, it is highly recommended for the corporations to have intelligent support for providing an accurate granting decision which naturally leads to minimizing the associated risk. In this research, a decision support model is proposed for loans granting. The proposed model applies a set of data mining techniques in a collaborative environment that aims at applying different techniques with considering their results according to the technique’s evaluation weight. The proposed model results present the recommendation for each customer’s loan granting a request to be either accepted or rejected. The proposed approach has been applied the on a loan granting dataset and the evaluation results revealed its superiority by 92% success in reaching high accurate decisions.