Framework for selecting thresholds for anomaly detection models and generating quantitative explanations

Abstract

A framework for extracting quantitative and comparable explanations in terms of feature-value ranges for anomaly detection models based on outlier scores is disclosed. In a first phase, outlier scores are computed for a data set. In a second phase, thresholds per feature, which are used to identify abnormal entries or records in the data set, are extracted. In a third phase, a map between feature-outlier scores and feature-value ranges is generated. The feature-value ranges represent explanations. The explanations may include extracting quantitative metrics to explain a model.

CPC Classifications