Automatically determining accuracy of a predictive model

A computer program product for determining accuracy of a trained predictive computational model, the computer program product comprising:

• a non-transitory computer readable storage medium having program instructions embodied therewith, the program instructions executable by a processor to cause the processor to perform a method, the method comprising:
• acquiring, by the processor, the trained predictive computational model from a database;
• applying a trained reduced complexity model to data used to train the trained predictive computational model, wherein the trained reduced complexity model is associated with the trained predictive computational model;
• selecting at least one metric;
• determining a quality indicator related to the at least one metric by:
• identifying the type of the at least one metric by comparing, based on one or more data points, the evaluated output of the trained predictive computational model to an evaluated output of the trained reduced complexity model,
• evaluating the output of the trained predictive computational model in relation to the type of the at least one metric, and
• generating, based on the evaluation of the trained predictive computational model, a threshold associated with the at least one metric;
• and
• determining the accuracy of the trained predictive computational model based on the quality indicator.

A system for determining accuracy of a trained predictive computational model, the system comprising:

• a memory;
• and
• a processor in communication with the memory, the processor being configured to perform operations comprising:
• acquiring, by the processor, the trained predictive computational model from a database;
• applying a trained reduced complexity model to data used to train the trained predictive computational model, wherein the trained reduced complexity model is associated with the trained predictive computational model;
• selecting at least one metric;
• determining a quality indicator related to the at least one metric by:
• identifying the type of the at least one metric by comparing, based on one or more data points, the evaluated output of the trained predictive computational model to an evaluated output of the trained reduced complexity model,
• evaluating the output of the trained predictive computational model in relation to the type of the at least one metric, and
• generating, based on the evaluation of the trained predictive computational model, a threshold associated with the at least one metric;
• and
• determining the accuracy of the trained predictive computational model based on the quality indicator.