Credit rating analysis using adaptive fuzzy rule-based systems: an industry-specific approach

Abstract

This paper presents an analysis of credit rating using fuzzy rule-based systems. The disadvantage of the models used in previous studies is that it is difficult to extract understandable knowledge from them. The root of this problem is the use of natural language that is typical for the credit rating process. This problem can be solved using fuzzy logic, which enables users to model the meaning of natural language words. Therefore, the fuzzy rule-based system adapted by a feed-forward neural network is designed to classify US companies (divided into the finance, manufacturing, mining, retail trade, services, and transportation industries) and municipalities into the credit rating classes obtained from rating agencies. Features are selected using a filter combined with a genetic algorithm as a search method. The resulting subsets of features confirm the assumption that the rating process is industry-specific (i.e. specific determinants are used for each industry). The results show that the credit rating classes assigned to bond issuers can be classified with high classification accuracy using low numbers of features, membership functions, and if-then rules. The comparison of selected fuzzy rule-based classifiers indicates that it is possible to increase classification performance by using different classifiers for individual industries.

Forecasting Corporate Financial Performance Using Sentiment in Annual Reports for Stakeholders’ Decision-Making

“…The input attributes were collected for U.S. companies in the year 2008, while the output financial performance (Z-score) was evaluated for the year 2010, and the change in the financial performance was measured as Z-score in 2010 related to its value in 2008. Following previous studies (Hajek 2012), we excluded the companies from the mining and financial industries to prevent problems with both industry-specific attributes and different financial performance evaluation. As a result, we were able to collect data for 448 U.S. companies, 199 of them classified into "safe zone", 172 classified into the "grey zone", and 44 into the "distress zone" category.…”

“…have been applied to predict future financial distress. These approaches have evolved from the use of univariate and multivariate statistical models (Altman 1968) to recent use of artificial intelligence (AI) methods such as neural networks (NNs) (Wilson, Sharda 1994;Hajek 2011;Cimpoeru 2011), support vector machines (SVMs) (Huang et al 2004;Hajek, Olej 2011), decision trees (Hajek, Michalak 2013), fuzzy rule-based systems (Chen et al 2011;Hajek 2012), or evolutionary algorithms (Varetto 1998). Comparative reviews of the modes can be found in Bellovary et al (2007), Ravi Kumar and Ravi (2007), or Kirkos (2012).…”

Defuzzification methods in intuitionistic fuzzy inference systems of Takagi-Sugeno type: The case of corporate bankruptcy prediction

“…Evolutionary algorithms have shown promising results for other generalizations of FISs [33,34,35]. Finally, we recommend future studies on related problems such as credit rating prediction [36].…”

Predicting corporate investment/non-investment grade by using interval-valued fuzzy rule-based systems—A cross-region analysis

“…A wide range of AI methods have been applied to predict credit ratings, including statistical classifiers [3], decision trees [1], neural networks (NNs) [4], [5], support vector machines (SVMs) with both supervised [6], [7] and semi-supervised learning [8], case-based reasoning [9], artificial immune systems [10], rough sets [11], fuzzy rule-based systems (FRBSs) [12], and ensemble approaches [10], [13]. Recent efforts have also indicated that AI methods should be integrated into the feature selection process to improve prediction accuracy [1].…”