Accuracy of value-at-risk model in commercial banks

Risk in banks is increasing day by day due to variety of reasons. The history of banking is full of failures (Minor as well as major). It is argued that many of these failures were due to the fact that the risks were not identified and managed properly. As per the RBI guidelines issued in October 1999, there are three major types of risks encountered by the banks viz., credit risk, market risk and operational risk. In order to manage market risks, major trading institutions have developed large scale risk measurement models. While approaches may differ, all such models measure and aggregate market risks in current positions at a highly detailed level. The models employ a standard risk metric, VaR, which is a lower tail percentile for the distribution of profit and loss (P&L). VaR has become a standard measure of financial market risk that is increasingly used by other financial and even nonfinancial firms as well. The present study focuses on the performance of select banks using VaR models. The banks taken for the study are HDFC Bank, ICICI Bank, ING Vysya Bank, State Bank of India, and South Indian Bank. The data obtained from the databases - Press and Capital Line Plus and NSE. The data for the study collected for period of 2005 to 2007. The data is analyzed by using skewness; kurtosis.

After performing t-test we have found that returns of ING Vysya Bank Ltd and South Indian Bank Ltd are not satisfactory as they are highly varied while return of all the other Banks are satisfactory. Comparing the VaR model, we can note that though returns of South Indian Bank Ltd are highly varying, its VaR model is accurate. It has always predicted correctly the maximum loss which an individual encounters. VaR model has violated the most in our sample, but its return is consistent. To conclude we can say that, commercial banks in India follow a better technique of forecasting value-at-risk.