A model for the classification of companies credit risk
DOI:
https://doi.org/10.1590/S1519-70772008000100003Keywords:
Credit risk model, Default event, Publicly traded companies, Logistic regression, Financial ratiosAbstract
The process of credit risk management in financial institutions has been revised in recent years. In this context, large banks have developed and implemented several new techniques for measuring borrowers credit risk. This research aims to develop a risk classification model to assess the credit risk of companies in the Brazilian market. The model was built based on a sample of publicly traded companies classified as solvent or insolvent during the period from 1994 to 2004. Logistic regression was used to develop the model. The independent variables of the model are financial ratios, calculated from the financial statements and used as proxies of companies economic and financial situation. The validation of the model was done using the Jackknife method and a ROC Curve. The results of the study indicate that the risk classification model developed predicts default events one year prior to failure with good level of accuracy. The results also indicate that financial statements contain information that allow for the classification of companies as probably solvent or probably insolvent.Downloads
Downloads
Published
Issue
Section
License
The content of the article(s) published in the RC&F are of the entire liability of the authors, including with regard to the truth, updating and accuracy of data and information. The authors shall assign the rights in advance to the Department of Accounts and Actuarial Sciences of the FEA/USP, which shall permit the publication of extracts or of the whole, with prior permission, provided that the source is cited (Creative Commons – CCBY).
RC&F shall not charge a fee for the submission of articles. The submission of articles to RC&F shall imply that the author(s) authorizes/authorize its publication without the payment of author’s rights.
The submission of articles shall authorize the RC&F to adjust the text of the article(s) to their publication formats and if necessary, to make spelling, grammar and regulatory changes.