Market risk management of banks : Implications from the accuracy of value-at-risk forecasts

This paper adopts the backtesting criteria of the Basle Committee to compare the performance of a number of simple Value-at-Risk (VAR) models. These criteria provide a new standard on forecasting accuracy. Currently central banks in major money centres, under the auspices of the Basle Committee of the Bank of International settlement, adopt the VaR system to evaluate the market risk of their supervised banks. Banks are required to report VaRs to bank regulators with their internal models. These models must comply with Basle's backtesting criteria. If a bank fails the VaR backtesting, higher capital requirements will be imposed. VaR is a function of volatility forecasts. Past studies mostly conclude that ARCH and GARCH models provide better volatility forecasts. However, this paper finds that ARCH- and GARCH-based VaR models consistently fail to meet Basle's backtesting criteria. These findings suggest that the use of ARCH- and GARCH-based models to forecast their VARs is not a reliable way to manage a bank's market risk. Copyright © 2003 John Wiley & Sons, Ltd.