Black-Box Anomaly Attribution

Abstract: When the prediction of a black-box machine learning model deviates from the true observation, what can be said about the reason behind that deviation? This is a fundamental and ubiquitous question that the end user in a business or industrial AI application often asks. The deviation may be due to a sub-optimal black-box model, or it may be simply because the sample in question is an outlier. In either case, one would ideally wish to obtain some form of attribution score -- a value indicative of the extent to which an input variable is responsible for the anomaly. In the present paper we address this task of anomaly attribution,'' particularly in the setting in which the model is black-box and the training data are not available. Specifically, we propose a novel likelihood-based attribution framework we call thelikelihood compensation (LC),'' in which the responsibility score is equated with the correction on each input variable needed to attain the highest possible likelihood. We begin by showing formally why mainstream model-agnostic explanation methods, such as the local linear surrogate modeling and Shapley values, are not designed to explain anomalies. In particular, we show that they are deviation-agnostic,'' namely, that their explanations are blind to the fact that there is a deviation in the model prediction for the sample of interest. We do this by positioning these existing methods under the unified umbrella of a function family we call theintegrated gradient family.'' We validate the effectiveness of the proposed LC approach using publicly available data sets. We also conduct a case study with a real-world building energy prediction task and confirm its usefulness in practice based on expert feedback.