An Investigation into Accuracy of CAMEL Model of Banking Supervision Using Rough Sets

Abstract

Application of intelligent methods in banking becomes a challenging issue and acquiring special attention of banking supervisors and policy makers. Intelligent methods like rough set theory (RST), fuzzy set and genetic algorithm contribute significantly in multiple areas of banking and other important segments of financial sector. CAMEL is a useful tool to examine the safety and soundness of various banks and assist the banking regulators to ward off any potential risk which may lead to bank failure. RST approach may be applied for verifying authenticity and accuracy of CAMEL model and this chapter invites reader’s attention towards this relatively new and unique application of RST. The results of CAMEL model have been widely accepted by banking regulators for the purpose of assessing the financial health of banks. In this chapter we have considered ten largest public sector Indian banks on the basis of their deposit-base over a five-year period (2008–2009 to 2012–2013). The analysis of financial soundness of banks is structured under two parts. Part I is devoted to ranking of these banks on the basis of performance indices of their capital adequacy (C), asset quality (A), management efficiency (M), earnings (E) and liquidity (L). Performance analysis has been carried out in terms of two alternative approaches so as to bring implications with regard to their rank accuracy. We named these approaches as Unclassified Rank Assignment Approach and Classified Rank Assignment Approach. Part II presents analysis of accuracy of ranks obtained by CAMEL model for both the approaches that is for Unclassified Rank Assignment Approach and for Classified Rank Assignment in terms of application of Rough Set Theory (RST). The output of CAMEL model (ranking of banks for both approaches) is given as input to rough set for generating rules and for finding the reduct and core. The accuracy of the ranking generated by the CAMEL model is verified using lower and upper approximation. This chapter demonstrates the accuracy of Ranks generated by CAMEL model and decisions rules are generated by rough set method for the CAMEL model. Further, the most important attribute of CAMEL model is identified as risk-adjusted capital ratio, CRAR under capital adequacy attribute and results generated by rough set theory confirm the accuracy of the Ranks generated by CAMEL Model for various Indian public- sector banks.