Abstract:This paper presents the modelling possibilities of kernel-based approaches to a complex real-world problem, i.e. corporate and municipal credit rating classification. Based on a model design that includes data pre-processing, the labelling of individual parameter vectors using expert knowledge, the design of various support vector machines with supervised learning as well as kernel-based approaches with semi-supervised learning, this modelling is undertaken in order to classify objects into rating classes. The… Show more
“…It was shown that support vector machines significantly outperform logistic regression models, particularly under the condition of small training samples and high variance of the input data. Further, in 2010 Peter Hajek and Vladimır Olej [16] have presented the modeling possibilities of kernel-based approaches to a complex real-world problem, i.e. corporate and municipal credit rating classification.…”
ABSTRACT.This paper presents a binary classification scheme for investment class rating using support vector machine (SVM). The suggested SVM model is trained offline and takes twelve financial ratios as attributes from different standard investment companies as inputs and correctly classify whether it is a good investment grade or bad investment grade company as output. The overall performance of SVM strongly depends on the regularization parameter C and kernel parameter σ. Hence, we propose the PSO based optimization technique using mean square error (MSE) as the fitness function to optimize the value of C and σ. The proposed scheme is implemented using Matlab and Libsvm tool. Comparison is made in terms of different performance measures like classification accuracy, sensitivity, specificity, precision, confusion matrix etc. From experimental results and analysis, it is observed that the proposed scheme has a superior performance as compared to SVM based approach without parameter optimization and neural network based scheme.
General TermsSupport Vector Machine, Binary Classification et al.
“…It was shown that support vector machines significantly outperform logistic regression models, particularly under the condition of small training samples and high variance of the input data. Further, in 2010 Peter Hajek and Vladimır Olej [16] have presented the modeling possibilities of kernel-based approaches to a complex real-world problem, i.e. corporate and municipal credit rating classification.…”
ABSTRACT.This paper presents a binary classification scheme for investment class rating using support vector machine (SVM). The suggested SVM model is trained offline and takes twelve financial ratios as attributes from different standard investment companies as inputs and correctly classify whether it is a good investment grade or bad investment grade company as output. The overall performance of SVM strongly depends on the regularization parameter C and kernel parameter σ. Hence, we propose the PSO based optimization technique using mean square error (MSE) as the fitness function to optimize the value of C and σ. The proposed scheme is implemented using Matlab and Libsvm tool. Comparison is made in terms of different performance measures like classification accuracy, sensitivity, specificity, precision, confusion matrix etc. From experimental results and analysis, it is observed that the proposed scheme has a superior performance as compared to SVM based approach without parameter optimization and neural network based scheme.
General TermsSupport Vector Machine, Binary Classification et al.
“…This paper tried to compare backpropagation neural network as a benchmark with the new technique. Later, Cao et.al [15], Lee [16]and Hajek and Olej [17] compared SVM with the backprogation (BP) neural network, and traditional statistical methods such as; logistic regression (LR) and ordered probit regression (OPR) with Support Vector Machine (SVM).…”
Section: B Previous Studies On Bond Rating Predictionsmentioning
Islamic finance and capital market is one of the fastest growing segments of international financial markets. Recent innovations in Islamic finance and capital market have changed the terrain of the landscape of the financial industry. One of them is Islamic securities which are known as Sukuk. The use of Sukuk as the alternative to the existing conventional bond, has become increasingly popular in the last few years. They are used as a means of raising government finance through sovereign Sukuk issues, and means through which companies raise funds by issuing corporate Sukuk. In addition, theoretically there should be some differences in rating methodologies for bond and Sukuk because these two instruments are different in nature. Thus, it is the aim of this study to identify the important determinants in Sukuk Rating using data mining approach. The final model is then implemented into web application, called S-Rater.
“…These sources of finance influence the credit rating process of these entities. Municipal credit rating is based on the analysis of four categories of variables, namely economic, debt, financial, and administrative (Hajek and Olej 2011). Economic variables include socio-economic conditions such as population, unemployment, and local economy concentration.…”
Section: Variable Selection In Datasetsmentioning
confidence: 99%
“…The difficulty in designing such models lies in the fact that there are complex relations between financial and other variables. Recently, soft-computing methods such as neural networks (NNs) (Brennan and Brabazon 2004;Hajek 2010Hajek , 2011, support vector machines (Huang et al 2004;Lee 2007), artificial immune systems (Delahunty and O'Callaghan 2004), evolutionary algorithms (Brabazon and O'Neill 2006), case based reasoning (Lee 2007), and semi-supervised methods (Hajek and Olej 2011) have been used for both municipal and corporate credit rating analysis.…”
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.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.