Explainable contextual anomaly detection using quantile regression forests

Abstract

Traditional anomaly detection methods aim to identify objects that deviate from most other objects by treating all features equally. In contrast, contextual anomaly detection methods aim to detect objects that deviate from other objects within a context of similar objects by dividing the features into contextual features and behavioral features. In this paper, we develop connections between dependency-based traditional anomaly detection methods and contextual anomaly detection methods. Based on resulting insights, we propose a novel approach to inherently interpretable contextual anomaly detection that uses Quantile Regression Forests to model dependencies between features. Extensive experiments on various synthetic and real-world datasets demonstrate that our method outperforms state-of-the-art anomaly detection methods in identifying contextual anomalies in terms of accuracy and interpretability.

.Efficiency of regression models in the presences of outliers

“…The result showed that the selection of the parametric functions is still guided by the jittering technique. (Li & Leeuwen, (2023) developed connections between dependency-based traditional anomaly detection methods for outliers detection and contextual anomaly detection methods using Quantile Regression Forests. ( Muspratt , &Mammadov,(2023)) applied a modified version of anomaly detection algorithm by enacting refined targeting capability based on the identification of subextreme anomalies.…”