Operational Risk Management: a statistical perspective

This work presents a statistical model for operational risk management. We distinguish different types of operational event, we model the probability of event occurrence (the frequency distribution) and the economic impact of the single event (the severity distribution), and then the aggregated distribution is obtained through convolution of frequency and severity, for each event type. The main problem is the parameters estimation of the severity distribution above a suitable threshold, that we consider as an unknown parameter to be estimated as well. An application to a case study is also presented.