Resampling simulation results for correlated events

A method for use with a computing system, the method comprising:

• receiving, for a plurality of correlated random variables, a simulation sample including a plurality of simulations, wherein each simulation includes a plurality of simulation results;
• generating a surrogate cumulative distribution model by estimating a plurality of surrogate model parameters based on the plurality of simulation results for the plurality of variables;
• based on the surrogate cumulative distribution model with the surrogate model parameters, selecting one or more subsets of the plurality of simulations;
• in each of one or more resampling iterations, until a sum of one or more respective discrepancy scores of the one or more subsets is determined to meet a predefined optimization threshold:
• computing the one or more discrepancy scores of the one or more subsets, wherein the discrepancy score is a measure of the deviation between a subset and the surrogate cumulative distribution model;
• based on the sum of the one or more discrepancy scores, sampling one or more resampled simulations for the plurality of correlated random variables from among the plurality of simulations that are included in the simulation sample and not already included in the one or more subsets;
• and
• replacing one or more simulations included in the one or more subsets with the one or more resampled simulations;
• and
• outputting the simulations included in the one or more subsets subsequently to performing the one or more resampling iterations.

A computing system, comprising:

• a processor configured to:
• receive, for a plurality of correlated random variables, a simulation sample including a plurality of simulations, wherein each simulation includes a plurality of simulation results;
• based on the plurality of simulation results, generate a surrogate cumulative distribution model;
• based on the surrogate cumulative distribution model, select a compressed subset of the plurality of simulations;
• in each of one or more resampling iterations, until a discrepancy score of the compressed subset is determined to be below a predetermined discrepancy threshold:
• compute the discrepancy score of the compressed subset;
• based on the discrepancy score, sample one or more resampled simulations for the plurality of correlated random variables from among the plurality of simulations that are included in the simulation sample and not already included in the compressed subset;
• and
• replace one or more simulations included in the compressed subset with the one or more resampled simulations;
• and
• output the simulations included in the compressed subset subsequently to performing the one or more resampling iterations.