Title: A hybrid model for customer credit scoring in stock brokerages using data mining approach

Authors: Rahmat Houshdar Mahjoub; Amir Afsar

Addresses: Department of Information Technology, School of Engineering, University of Qom, Ghadir Blv., Qom, Iran ' Department of Operations Management, School of Management and Economics, Tarbiat Modares University, Jalal AleAhmad Blv., P.O. Box 14115-111, Tehran, Iran

Abstract: Credit scoring has become a challenging issue for stock brokerages, as the credit industry has been facing high competition during the past decade. Many methods have been suggested to credit scoring in the literature. The purpose of this study is to set up a hybrid model for customer credit scoring in Iran's National Investment Brokerage. It also provides a way to pay appropriate facilities as tools for CRM. So, after the data pre-processing step, we convert refined dataset into RFM model. Customers were clustered using two clustering algorithms, self-organising map (SOM) and K-means. In both methods, the best optimum number of clusters was calculated at ten. Afterwards, the clusters ranked using TOPSIS and the top three clusters were considered as the target customers. Eventually, the credit score of the superior cluster members were calculated. Coefficient facilities granted to the top three clusters respectively are 0.271, 0.173 and 0.556.

Keywords: credit scoring; customer relationship management; CRM; self-organising map; SOM; K-means; data mining; TOPSIS; stock brokerages.

DOI: 10.1504/IJBIS.2019.100279

International Journal of Business Information Systems, 2019 Vol.31 No.2, pp.195 - 214

Received: 12 Jun 2017
Accepted: 09 Sep 2017
Published online: 24 Jun 2019 *

Full-text access for editors Full-text access for subscribers Purchase this article Comment on this article