Measuring AI Systems Beyond Accuracy

Abstract: Current test and evaluation (T&E) methods for assessing ML system performance often rely on incomplete metrics. Testing is additionally often siloed from the other phases of the ML system lifecycle. Research investigating cross-domain approaches to ML T&E is needed to drive the state of the art forward and to build an AI engineering discipline. This paper advocates for a robust, integrated approach to testing by outlining six key questions for guiding a holistic T&E strategy.