Determining system performance without ground truth

A system comprising:

• a memory having computer readable instructions;
• and
• one or more processors for executing the computer readable instructions, the computer readable instructions controlling the one or more processors to perform operations comprising:
• receiving a trained model and one or more generator models, the trained model having been trained on training data, the one or more generator models being configured to produce synthetic training data that is representative of the training data;
• using the trained model on testing data to produce labeled testing data;
• using, by the one or more processors, the labeled testing data to train a proxy model;
• using, by the one or more processors, the proxy model on the synthetic training data to produce predictions;
• and
• determining, by the one or more processors, performance of the trained model based on the predictions by the proxy model.

A computer program product comprising a computer readable storage medium having program instructions embodied therewith, the program instructions executable by a processor to cause the processor to perform operations comprising:

• receiving a trained model and one or more generator models, the trained model having been trained on training data, the one or more generator models being configured to produce synthetic training data that is representative of the training data;
• using the trained model on testing data to produce labeled testing data;
• using, by the processor, the labeled testing data to train a proxy model;
• using, by the processor, the proxy model on the synthetic training data to produce predictions;
• and
• determining, by the processor, performance of the trained model based on the predictions by the proxy model.