Abstract: This paper investigates the frequency of extreme events for three LIFFE futures contracts for the calculation of minimum capital risk requirements (MCRRs). We propose a semi-parametric approach where the tails are modelled by the Generalised Pareto Distribution and smaller risks are captured by the empirical distribution function. We compare the capital requirements from this approach with those calculated from the unconditional density and from a conditional density- a GARCH(1,1) model. Our primary finding is that for both in-sample and hold-out samples, our extreme value approach yields superior results than either of the other two models which do not explicitly model the tails of the return distribution. Since the use of these internal models will be permitted under the EC-CAD II, they could be widely adopted in the near future by European financial institutions for determining capital adequacies. Hence, close scrutiny of competing models is required to avoid a potentially costly misallocation of capital resources while at the same time ensuring the safety of the financial system.