How to gauge credit risk: an investigation based on data envelopment analysis and the Markov chain model

• Autores: Su-Lien Lu, Kuo-Jung Lee, Ming-Lun Zou
• Localización: Applied financial economics, ISSN 0960-3107, Vol. 22, Nº. 10-12, 2012, págs. 887-897
• Idioma: inglés
• Texto completo no disponible (Saber más ...)
• Resumen

  • Credit risk management is one of the most important issues in the financial services industry. This article proposes a formal methodology based on Data Envelopment Analysis (DEA) and the Markov chain model to assess the credit risk of major enterprises in Taiwan. The first step of this method involves the application of factor analysis to filter financial data according to dimensions and ratios. Second, we derive the credibility scores of domestic corporations with DEA. Third, regression analysis and discriminant analysis validate the results of DEA credibility scores. At this stage, we find that most firms in Taiwan need to improve their respective financial credibility. Fourth, we apply DEA credibility scores to the Markov chain model. Finally, we construct transition matrices to observe the transition process of the financial efficiency of the firms. The advantage of the proposed method is that it is simple to follow and implement, and its empirical results can enable banks and financial institutions to monitor their credit risk quite closely. By using this method, banks and other financial institutions will be able to make more efficient lending decisions and face the Basel Capital Accord in the future.