Characterizing failures of a machine learning model based on instance features

A system, comprising:

• at least one processor;
• memory in electronic communication with the at least one processor;
• and
• instructions stored in the memory, the instructions being executable by the at least one processor to:
• receive, from a machine learning system that is trained to generate an output for a given test instance, a plurality of outputs for a plurality of test instances, the machine learning system including a plurality of machine learning models;
• identify label information associated with the plurality of test instances, the label information comprising feature labels associated with respective instances from the plurality of test instances and ground truth data corresponding to expected outputs of the machine learning system with respect to the plurality of test instances;
• compare the label information and the plurality of outputs to identify a set of error labels associated with a subset of outputs from the plurality of outputs that are inaccurate with respect to corresponding label information;
• compare label information associated with the subset of outputs and sets of outputs from respective machine learning models of the plurality of machine learning models;
• and
• generate a plurality of feature clusters comprising groupings of test instances from the plurality of test instances based on the feature labels and the set of error labels.

A non-transitory computer readable medium storing instructions thereon that, when executed by at least one processor, causes the at least one processor to:

• receive, from a machine learning system that is trained to generate an output for a given test instance, a plurality of outputs for a plurality of test instances, the machine learning system including a plurality of machine learning models;
• identify label information associated with the plurality of test instances, the label information comprising feature labels associated with respective instances from the plurality of test instances and ground truth data corresponding to expected outputs of the machine learning system with respect to the plurality of test instances;
• compare the label information and the plurality of outputs to identify a set of error labels associated with a subset of outputs from the plurality of outputs that are inaccurate with respect to corresponding label information;
• compare label information associated with the subset of outputs and sets of outputs from respective machine learning models of the plurality of machine learning models;
• and
• generate a plurality of feature clusters comprising groupings of test instances from the plurality of test instances based on the feature labels and the set of error labels.