Tail risk forecasting and its application to margin requirements in the commodity futures market

Abstract

This study presents a dynamic analysis framework called autoregressive conditional extreme value (AEV), designed for modeling the daily maximum drawdowns of commodity futures markets, using steel rebar futures as an illustrative example. The research demonstrates that AEV outperforms AR or generalized autoregressive conditional heteroskedasticity (GARCH)-type benchmark models in terms of in-sample fitting and out-of-sample forecasting accuracy. Notably, AEV's time-varying shape parameter (tail index) sensitively captures the clustering nature of tail risk and differentiates between long- and short-side markets. The study also presents theoretical findings regarding AEV-based value at risk (VaR) and expected shortfall (ES), and empirically measures and predicts the tail risk of the steel rebar futures market. Moreover, the research extends the methodology to create a dynamic margin model for Chinese commodity futures, showing that the AEV-based model effectively achieves the specified risk coverage targets and significantly reduces current exchange margin requirements.