Non-parametric estimation of operational risk losses adjusted for under-reporting

Abstract

Not all claims are reported when a database for financial operational risk is created. The probability of reporting increases with the size of the operational risk loss, and converges towards one for big losses. Losses in operational risk have different causes, and usually follow a wide variety of distributional shapes. Therefore, a method for modelling operational risk based on one or two parametric models is deemed to fail. In this paper, we introduce a semi-parametric method for modelling operational risk that is capable of taking under-reporting into account and being guided by prior knowledge of the distributional shape.

Keywords:

• Operational risk
• Solvency II
• Under-reporting
• Non-parametric smoothing
• Semiparametric kernel density estimation
• Tail flattening transformation
• Prior knowledge

Winning paper of the Operational Risk & Compliance Achievement Award 2007.

Winning paper of the Operational Risk & Compliance Achievement Award 2007.

Notes

Winning paper of the Operational Risk & Compliance Achievement Award 2007.

²Solvency II is the European regulation structure that specifies how insurance companies must manage their risks and reserve prudent solvency margins.

³SCR is the capital requirement of the insurance company. FSA increases its control when capital gets below SCR. When capital gets below the MCR, FSA can take over the management of the insurance company, and perhaps even stop for new underwriting of business.