Quantitative Finanical Risk Analysis by Advanced Monte Carlo Method

Description

Managing market risks necessitates their effective assessment, especially with regard to large losses that are often associated with “low-probability-high-consequence” scenarios. This project explores the application of an engineering reliability method called Subset Simulation recently developed by the principal investigator to quantitative financial risk analysis, focusing on problems related to market risks. Subset Simulation is a general Monte Carlo-based stochastic analysis algorithm. It was originally developed for solving first passage problems of civil and mechanical structures under stochastic loading, but it is applicable to general problems. The method is based on the simple idea that a small failure probability can be expressed as a product of larger conditional failure probabilities, thereby in principle converting a rare simulation problem into a sequence of more frequent simulation problems. In addition to estimating failure probabilities, Subset Simulation also provides information for statistical sensitivity analysis, through the statistical analysis of conditional samples generated during implementation.