STRUCTURED LIABILITY RISKS PARAMETRIZING AND FORECASTING SYSTEM PROVIDING COMPOSITE MEASURES BASED ON A REDUCED-TO-THE-MAX OPTIMIZATION APPROACH AND QUANTITATIVE YIELD PATTERN LINKAGE AND CORRESPONDING METHOD

摘要

Proposed is a system (10) providing a liability temperature measure (31) for liability systems (1) based on a time-dependent, composite indexing parameter (17). Measurement parameters assigned to parameterized liability risk drivers (311-313) are measured for generating the measured time-dependent, composite indexing parameter (17). The used liability risk drivers (311-313) are selected based on their impact to the measured variable composite index parameter and dynamically normalized to each other. The normalization is based on a defined transformation (151) applied to the final time series of the parameters providing individual set weights (1511,…,1513), wherein based on the weighted liability risk drivers (311-313) and sets of liability risk drivers (311-313), a minimum number (192) of liability risk drivers (311-313) in relation to maximized statistical significance is selected by applying an index assembly and validation unit (19), and wherein the index assembly and validation unit (19) provides the minimum number (192) of liability risk drivers (311-313) as a reduced set (161) of liability risk drivers out of all available liability risk drivers (16) using best fit characteristics (191). The driver selector (15) dynamically adapts the minimum number (192) of liability risk drivers (311-313) varying the liability risk drivers (311-313) in relation to the measured liability exposure signal (31) by periodic time response, wherein the time-dependent composite index parameter (17) is generated based on the adapted reduced set (161) of liability risk drivers (311-313).