Computing System and Method for Applying Monte Carlo Estimation to Determine the Contribution of Independent Input Variables Within Dependent Variable Groups on the Output of a Data Science Model

A computing platform is configured to, for a model object trained to output a score for an input data record, the input data record including a set of input variables that are arranged into groups based on dependencies, iterate the following for each respective input variable in each respective group: (a) identify a sample from a set of historical data records, (b) determine a first score for the sample, (c) determine a second score for the sample that is conditioned on the respective group in a given input data record, (d) select a random variable coalition within the respective group, (e) compute a group-specific contribution value for the respective input variable in the respective group, and (f) compute an iteration-specific contribution value for the respective input variable to the model output, and (vi) for each respective input variable, aggregate the iteration-specific contribution values and thereby determine an aggregated contribution value for the respective input variable.