Algorithmic Recourse in Abnormal Multivariate Time Series

TL;DR

This paper introduces RecAD, a framework for providing actionable recourse in multivariate time series anomalies by modeling external interventions and generating counterfactual explanations to restore normalcy.

Contribution

It presents RecAD, the first framework for algorithmic recourse in multivariate time series anomaly detection using backtracking counterfactual reasoning.

Findings

RecAD effectively identifies recourse actions on synthetic datasets.

RecAD successfully restores normality in real-world anomaly cases.

The framework outperforms baseline methods in anomaly recourse accuracy.

Abstract

Algorithmic recourse provides actionable recommendations to alter unfavorable predictions of machine learning models, enhancing transparency through counterfactual explanations. While significant progress has been made in algorithmic recourse for static data, such as tabular and image data, limited research explores recourse for multivariate time series, particularly for reversing abnormal time series. This paper introduces Recourse in time series Anomaly Detection (RecAD), a framework for addressing anomalies in multivariate time series using backtracking counterfactual reasoning. By modeling the causes of anomalies as external interventions on exogenous variables, RecAD predicts recourse actions to restore normal status as counterfactual explanations, where the recourse function, responsible for generating actions based on observed data, is trained using an end-to-end approach. Experiments on synthetic and real-world datasets demonstrate its effectiveness.