Anomaly Attribution with Likelihood Compensation
This work addresses the need for interpretability in black-box models, particularly for domain experts in fields like building energy management, though it appears incremental as it builds on existing principles for anomaly attribution.
The paper tackles the problem of explaining anomalous predictions in black-box regression models by formalizing it as a statistical inverse problem and proposing a new method called likelihood compensation to compute responsibility scores for input variables. The method was applied to a real-world building energy prediction task and validated with expert feedback.
This paper addresses the task of explaining anomalous predictions of a black-box regression model. When using a black-box model, such as one to predict building energy consumption from many sensor measurements, we often have a situation where some observed samples may significantly deviate from their prediction. It may be due to a sub-optimal black-box model, or simply because those samples are outliers. In either case, one would ideally want to compute a ``responsibility score'' indicative of the extent to which an input variable is responsible for the anomalous output. In this work, we formalize this task as a statistical inverse problem: Given model deviation from the expected value, infer the responsibility score of each of the input variables. We propose a new method called likelihood compensation (LC), which is founded on the likelihood principle and computes a correction to each input variable. To the best of our knowledge, this is the first principled framework that computes a responsibility score for real valued anomalous model deviations. We apply our approach to a real-world building energy prediction task and confirm its utility based on expert feedback.