Explaining accuracy drift in production data

A computer program product for explaining accuracy drift in production data, the computer program product comprising a computer readable storage medium having program instructions embodied therewith, wherein the computer readable storage medium is not a transitory signal per se, the program instructions executable by a processor to cause the processor to perform a method comprising:

• identifying, by the processor, an occurrence of accuracy drift by a trained model;
• identifying, by the processor, data associated with the accuracy drift, utilizing a drift detection model (DDM) constructed for the trained model;
• applying, by the processor, the data associated with the accuracy drift to a decision tree to determine a feature space and specific subset of the data causing the accuracy drift;
• analyzing, by the processor, a distribution of features within the feature space for the specific subset of the data causing the accuracy drift to determine specific features of the data causing the accuracy drift;
• and
• returning, by the processor, the specific features of the data causing the accuracy drift.

A system, comprising:

• a processor;
• and
• logic integrated with the processor, executable by the processor, or integrated with and executable by the processor, the logic being configured to:
• identify an occurrence of accuracy drift by a trained model;
• identify data associated with the accuracy drift, utilizing a drift detection model (DDM) constructed for the trained model;
• apply the data associated with the accuracy drift to a decision tree to determine a feature space and specific subset of the data causing the accuracy drift;
• analyze a distribution of features within the feature space for the specific subset of the data causing the accuracy drift to determine specific features of the data causing the accuracy drift;
• and
• return the specific features of the data causing the accuracy drift.