US 12,141,873 B2
Deep neural network assisted prediction using Monte Carlo simulations
Sunilkumar Muthyala, Hyderabad (IN); and Sreedhar Athikam, Monroe Township, NJ (US)
Assigned to S&P Global Inc., New York, NY (US)
Filed by S&P Global Inc., New York, NY (US)
Filed on Mar. 10, 2023, as Appl. No. 18/181,768.
Prior Publication US 2024/0303741 A1, Sep. 12, 2024
Int. Cl. G06Q 40/06 (2012.01)
CPC G06Q 40/06 (2013.01) 24 Claims
OG exemplary drawing
 
1. A computer-implemented method for testing prototype indices, the method comprising:
using a number of processors to perform the steps of:
receiving input of a number of historical index values;
performing a number of Monte Carlo simulations based on the historical index values to predict future index values;
calculating a number of attributes of the historical index values;
correlating the Monte Carlo simulations with the attributes to identify a filtered subset of predicted future index values having an accuracy above a defined threshold;
feeding the filtered subset of predicted future index values into a deep neural network (DNN), wherein the deep neural network comprises a sequential recurrent neural network; and
outputting, by the DNN, a confidence score for each of the filtered subset of predictive future index values.