Evaluating Tree Explanation Methods for Anomaly Reasoning: A Case Study of SHAP TreeExplainer and TreeInterpreter
This work addresses the need for reliable model explanations in anomaly detection for cloud-computing applications, but it is incremental as it compares existing methods without introducing new ones.
The paper tackled the problem of evaluating explanation methods for tree-based models in anomaly detection, finding that SHAP TreeExplainer's consistency guarantees did not improve explanation performance compared to TreeInterpreter in a cloud-computing case study.
Understanding predictions made by Machine Learning models is critical in many applications. In this work, we investigate the performance of two methods for explaining tree-based models- Tree Interpreter (TI) and SHapley Additive exPlanations TreeExplainer (SHAP-TE). Using a case study on detecting anomalies in job runtimes of applications that utilize cloud-computing platforms, we compare these approaches using a variety of metrics, including computation time, significance of attribution value, and explanation accuracy. We find that, although the SHAP-TE offers consistency guarantees over TI, at the cost of increased computation, consistency does not necessarily improve the explanation performance in our case study.