Robust estimation of operational risk

Applying Robust Methods to Operational Risk Modeling

Non - parametric Estimation of Operational Risk and Expected Shortfall

This paper proposes improvements to advanced measurement approach (AMA) to estimating operational risks, and applies the improved methods to US business losses categorised into five business lines and three event types operational losses. The AMA involves, among others, modelling a loss severity distribution and estimating the Expected Loss and the 99.9% operational value-at-risk (OpVaR). These...

Option Pricing in the Presence of Operational Risk

In this paper we distinguish between operational risks depending on whether the operational risk naturally arises in the context of model risk. As the pricing model exposes itself to operational errors whenever it updates and improves its investment model and other related parameters. In this case, it is no longer optimal to implement the best model. Generally, an option is exercised in a jump-...

Robust Estimation via Robust Gradient Estimation

We provide a new computationally-efficient class of estimators for risk minimization. We show that these estimators are robust for general statistical models: in the classical Huber ǫ-contamination model and in heavy-tailed settings. Our workhorse is a novel robust variant of gradient descent, and we provide conditions under which our gradient descent variant provides accurate estimators in a g...

Bayesian Robust Estimation of Systematic Risk Using Product Partition Models

We consider Bayesian estimation of the systematic risk of a share using product partition models (PPM). The cluster structure of the PPM is used to derive a robust Bayes estimator of beta and also to identify outliers or clusters of observations. The procedure is implemented considering independent scale mixture of normals for the error terms. The results are illustrated with an application to ...