Municipal credit rating modelling by neural networks

The paper presents the modelling possibilities of neural networks on a complex real-world problem, i.e. municipal credit rating modelling. First, current approaches in credit rating modelling are introduced. Second, previous studies on municipal credit rating modelling are analyzed. Based on this analysis, the model is designed to classify US municipalities (located in the State of Connecticut) into rating classes. The model includes data pre-processing, the selection process of input variables, and the design of various neural networks' structures for classification. The selection of input variables is realized using genetic algorithms. The input variables are extracted from financial statements and statistical reports in line with previous studies. These variables represent the inputs of neural networks, while the rating classes from Moody's rating agency stand for the outputs. In addition to exact rating classes, data are also labelled by four basic rating classes. As a result, the classification accuracies and the contributions of input variables are studied for the different number of classes. The results show that the rating classes assigned to bond issuers can be classified with a high accuracy rate using a limited subset of input variables.

[1]  P. Farnham,et al.  Municipal Bond Ratings: New Results, New Directions , 1982 .

[2]  Robert W. Ingram,et al.  The Association Between Municipal Accounting Information and Bond Rating Changes , 1982 .

[3]  Karen M. Hogan,et al.  Does the market perceive a difference in rating agencies , 1999 .

[4]  Ecole Supérieure,et al.  Assessment of local financial risk : the determinants of the rating of European local authorities - An empirical study over the period 1995 - 1998 , 1998 .

[5]  Stella Cheung,et al.  Provincial Credit Ratings in Canada: An Ordered Probit Analysis , 1996 .

[6]  Thomas G. Calderon,et al.  A roadmap for future neural networks research in auditing and risk assessment , 2002, Int. J. Account. Inf. Syst..

[7]  Daniel L. Rubinfeld,et al.  CREDIT RATINGS AND THE MARKET FOR GENERAL OBLIGATION MUNICIPAL BONDS , 1973, National tax journal.

[8]  Stephen Thomas,et al.  Modelling sovereign credit ratings: Neural networks versus ordered probit , 2006, Expert Syst. Appl..

[9]  Petr Hájek,et al.  Municipal Creditworthiness Modelling by Kernel-Based Approaches with Supervised and Semi-supervised Learning , 2009, EANN.

[10]  Salwa Ammar,et al.  Using Fuzzy Rule–Based Systems to Evaluate Overall Financial Performance of Governments: An Enhancement to the Bond Rating Process , 2001 .

[11]  Willard T. Carleton,et al.  Statistical Credit Scoring of Municipal Bonds , 1969 .

[12]  Thore Graepel,et al.  Neural Networks in Economics , 1999 .

[13]  Soushan Wu,et al.  Credit rating analysis with support vector machines and neural networks: a market comparative study , 2004, Decis. Support Syst..

[14]  Allen Michel,et al.  Municipal Bond Ratings: A Discriminant Analysis Approach , 1977 .

[15]  George E. Peterson.  Measuring local government credit risk and improving creditworthiness , 1998 .

[16]  Richard T. Redmond,et al.  Expert systems for bond rating: a comparative analysis of statistical, rule‐based and neural network systems , 1993 .

[17]  Clive W. J. Granger,et al.  Developments in the Nonlinear Analysis of Economic Series , 1991 .

[18]  Hannu Vanharanta,et al.  Using the Self-Organizing Map as a Visualization Tool in Financial Benchmarking , 2003, Inf. Vis..

[19]  Julian F. Miller,et al.  Genetic and Evolutionary Computation — GECCO 2003 , 2003, Lecture Notes in Computer Science.

[20]  Mu-Chen Chen,et al.  Credit scoring with a data mining approach based on support vector machines , 2007, Expert Syst. Appl..

[21]  Petr Hájek,et al.  Municipal Creditworthiness Modelling by Radial Basis Function Neural Networks and Sensitive Analysis of Their Input Parameters , 2009, ICANN.

[22]  Young-Chan Lee,et al.  Application of support vector machines to corporate credit rating prediction , 2007, Expert Syst. Appl..

[23]  David A. Elizondo,et al.  Bankruptcy forecasting: An empirical comparison of AdaBoost and neural networks , 2008, Decis. Support Syst..

[24]  Christian Lebiere,et al.  The Cascade-Correlation Learning Architecture , 1989, NIPS.

[25]  Simon Haykin,et al.  Neural Networks: A Comprehensive Foundation , 1998 .

[26]  J. Galindo,et al.  Credit Risk Assessment Using Statistical and Machine Learning: Basic Methodology and Risk Modeling Applications , 2000 .

[27]  R. Kaplan,et al.  Statistical Models of Bond Ratings: A Methodological Inquiry , 1979 .

[28]  Anthony Brabazon,et al.  Grammatical Evolution And Corporate Failure Prediction , 2002, GECCO.

[29]  John J. Siegfried,et al.  THE DISTRIBUTIONAL EFFECTS OF A SALES TAX ON SERVICES , 1991, National Tax Journal.

[30]  Shigeo Abe.  Support Vector Machines for Pattern Classification , 2010, Advances in Pattern Recognition.

[31]  Patrick Brézillon,et al.  Lecture Notes in Artificial Intelligence , 1999 .

[32]  Kee S. Kim,et al.  Predicting bond ratings using publicly available information , 2005, Expert Syst. Appl..

[33]  Gerald J. Miller,et al.  Handbook of Debt Management , 1996 .

[34]  James H. Garrett,et al.  Engineering applications of neural networks , 1993, J. Intell. Manuf..

[35]  Li-Yen Shue,et al.  The development of a decision model for liquidity analysis , 2000 .

[36]  K. K. Raman,et al.  Financial Reporting and Municipal Bond Rating Changes , 1981 .

[37]  Peter E. Kennedy,et al.  Combining Bond Rating Forecasts Using Logit , 2001 .

[38]  Anthony Brabazon,et al.  Corporate Bond Rating Using Neural Networks , 2004, IC-AI.

[39]  Petr Hájek,et al.  Debt analysis of Czech municipalities , 2009 .

[40]  Paul Newbold,et al.  PREDICTING INDUSTRIAL BOND RATINGS WITH A PROBIT MODEL AND FUNDS FLOW COMPONENTS , 1988 .

[41]  Michael Doumpos,et al.  Probabilistic neural networks for the identification of qualified audit opinions , 2007, Expert Syst. Appl..

[42]  Shigeo Abe,et al.  Support Vector Machines for Pattern Classification (Advances in Pattern Recognition) , 2005 .

[43]  Donald F. Specht,et al.  Probabilistic neural networks , 1990, Neural Networks.

[44]  Vladimír Olej.  MUNICIPAL CREDITWORTHINESS MODELLING BY ARTIFICIAL IMMUNE SYSTEMS , 2010 .

[45]  Virginia Torczon,et al.  On the Convergence of Pattern Search Algorithms , 1997, SIAM J. Optim..

[46]  Anthony L. Loviscek,et al.  What Is in a Municipal Bond Rating , 1990 .

[47]  An-Sing Chen,et al.  Application of Neural Networks to an Emerging Financial Market: Forecasting and Trading the Taiwan Stock Index , 2001, Comput. Oper. Res..

[48]  Katsutoshi Yada,et al.  Is this brand ephemeral? A multivariate tree-based decision analysis of new product sustainability , 2007, Decis. Support Syst..

[49]  Petr Hájek,et al.  Municipal Creditworthiness Modelling by Kohonen's Self-Organizing Feature Maps and Fuzzy Logic Neural Networks , 2008, ICANN.

[50]  James R. Marsden,et al.  Duplicating Moody's Municipal Credit Ratings , 1980 .

[51]  Kyungsup Kim,et al.  The cluster-indexing method for case-based reasoning using self-organizing maps and learning vector quantization for bond rating cases , 2001, Expert Syst. Appl..