Prediction of Financial Strength Ratings Using Machine Learning and Conventional Techniques

Abdou, H. A., Abdallah, W. M., Mulkeen, J., Ntim, C. G., & Wang, Y. (2017) ‘Prediction of financial strength ratings using machine learning and conventional techniques’, Investment Management and Financial Innovation, 14(4), pp. 194-211, (Accepted 20th December, 2017)

32 Pages Posted: 19 Jan 2018

See all articles by Hussein Abdou

Hussein Abdou

The Lancashire School of Business & Enterprise; Department of Management, Faculty of Commerce, Mansoura University

Wael Abd Allah

Misr International University (MIU)

James Mulkeen

University of Salford - Business School

Collins G. Ntim

University of Southampton Business School, UK; University of Southampton

Yan Wang

Leicester Business School, De Montfort University

Date Written: December 20, 2017

Abstract

Financial strength ratings (FSRs) have become more significant particularly since the recent financial crisis of 2007-09 where rating agencies failed to forecast defaults and the downgrade of some banks. The aim of this paper is to predict Capital Intelligence banks’ financial strength ratings (FSRs) group membership using machine learning and conventional techniques. Here we use five different statistical techniques, namely CHAID, CART, multilayer-perceptron neural networks, discriminant analysis and logistic regression. We also use three different evaluation criteria namely average correct classification rate, misclassification cost and gains charts. Our data is collected from Bankscope database for the Middle Eastern commercial banks by reference to the first decade in the 21st Century. Our findings show that when predicting bank FSRs during the period 2007-2009, discriminant analysis is surprisingly superior to all other techniques used in this paper. When only machine learning techniques are used, CHAID outperform other techniques. In addition, our findings highlight that when a random sample is used to predict bank FSRs, CART outperform all other techniques. Our evaluation criteria have confirmed our findings and both CART and discriminant analysis are superior to other techniques in predicting bank FSRs. This has implications for Middle Eastern banks as we would suggest that improving their bank FSR can improve their presence in the market.

Keywords: FSR Group Membership; Capital Intelligence; Machine Learning Techniques; Conventional Techniques; Middle East

JEL Classification: G21; G24; C14; C38

Suggested Citation

Abdou, Hussein and Abd Allah, Wael and Mulkeen, James and Ntim, Collins G. and Wang, Yan, Prediction of Financial Strength Ratings Using Machine Learning and Conventional Techniques (December 20, 2017). Abdou, H. A., Abdallah, W. M., Mulkeen, J., Ntim, C. G., & Wang, Y. (2017) ‘Prediction of financial strength ratings using machine learning and conventional techniques’, Investment Management and Financial Innovation, 14(4), pp. 194-211, (Accepted 20th December, 2017). Available at SSRN: https://ssrn.com/abstract=3100986

Hussein Abdou (Contact Author)

The Lancashire School of Business & Enterprise ( email )

The Lancashire Law School
Corporation Street
Preston, PR1 2HE
United Kingdom
00441772894700 (Phone)

Department of Management, Faculty of Commerce, Mansoura University ( email )

Mansoura, 35516
Egypt

Wael Abd Allah

Misr International University (MIU) ( email )

KM 28 Cairo - Ismailia Road (Ahmed Orabi District)
Cairo, 11341
Egypt

James Mulkeen

University of Salford - Business School ( email )

University of Salford
M5 4WT Salford, Lancashire M5 4WT
United Kingdom

Collins G. Ntim

University of Southampton Business School, UK ( email )

Southampton Business School
Highfield
Southampton, England SO17 IBJ
United Kingdom
+44 (0) 238059 4285 (Phone)
+44 (0) 238059 3844 (Fax)

HOME PAGE: http://www.southampton.ac.uk/business-school/about/staff/cgn1n11.page

University of Southampton ( email )

Southampton, SO17 1BJ
United Kingdom

Yan Wang

Leicester Business School, De Montfort University ( email )

The Gateway
, Leicester, LE1 9BH
United Kingdom

Register to save articles to
your library

Register

Paper statistics

Downloads
548
Abstract Views
1,254
rank
49,682
PlumX Metrics