Description: This paper demonstrates that extreme value theory (EVT) can be used as a tool to model policyholder behavior in the extreme tail. This paper applies EVT to the study of variable annuity dynamic lapse behavior in the extreme tail. It illustrates a process whereby a company can fully model policyholder behavior, including the extreme tail, with existing data. No judgment about the extremal behavior is necessary.

Description: For the purposes of risk management and stress testing, we characterize a spectrum of plausible extreme events, that we dub Grey Swans, by introducing a probabilistic method involving the concentration of measure phenomenon. As a result, stress tests can be triaged according to severity, probability and, now, information-based plausibility.

Description: This paper provides a description of a system using statistical spatial methods for measuring, analysis, and managing ERM losses. An example of its application to a delinquency rate in a residential mortgage portfolio analysis demonstrates how this methodology can help decrease a company’s exposure in high-risk areas and increase exposure in low-risk areas.

Description: The initial risk reserves in collective risk models vary according to the underlying claim distribution, and a suitable level of ruin probability. A thorough analysis of the needed initial surplus for various ruin probability levels is provided in eight meaningful examples. The claim distributions are drawn from various fields of insurance, including property damage and liability insurance.

Description: An insurance product’s return on required equity demonstrates how successfully its results are covering the company’s basic capital. Using some simplified assumptions, it is possible to calculate this return ratio and decompose it without a full projection of liabilities.

Description: This paper examines the potential impact of increasing negative commentary by social media users in multiple forums, which can erode the “reputation capital” of a utility. It also offers an approach for successfully addressing that risk and integrating social media risk management practices into existing utility enterprise risk management (ERM) programs.

Description: This paper introduces a re-rating formula which calculates proposed rates directly by means of fully developed and trended loss costs and current class differentials. From 2007 Enterprise Risk Management Symposium, M-AS07-1.