Explainable Anomaly Detection: Counterfactual driven What-If Analysis

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Cummins, Logan, Sommers, Alexander, Mittal, Sudip, Rahimi, Shahram, Seale, Maria, Jaboure, Joseph, Arnold, Thomas
Format: Preprint
Published: 2024
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866917755089846272
author Cummins, Logan
Sommers, Alexander
Mittal, Sudip
Rahimi, Shahram
Seale, Maria
Jaboure, Joseph
Arnold, Thomas
author_facet Cummins, Logan
Sommers, Alexander
Mittal, Sudip
Rahimi, Shahram
Seale, Maria
Jaboure, Joseph
Arnold, Thomas
contents There exists three main areas of study inside of the field of predictive maintenance: anomaly detection, fault diagnosis, and remaining useful life prediction. Notably, anomaly detection alerts the stakeholder that an anomaly is occurring. This raises two fundamental questions: what is causing the fault and how can we fix it? Inside of the field of explainable artificial intelligence, counterfactual explanations can give that information in the form of what changes to make to put the data point into the opposing class, in this case "healthy". The suggestions are not always actionable which may raise the interest in asking "what if we do this instead?" In this work, we provide a proof of concept for utilizing counterfactual explanations as what-if analysis. We perform this on the PRONOSTIA dataset with a temporal convolutional network as the anomaly detector. Our method presents the counterfactuals in the form of a what-if analysis for this base problem to inspire future work for more complex systems and scenarios.
format Preprint
id arxiv_https___arxiv_org_abs_2408_11935
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle Explainable Anomaly Detection: Counterfactual driven What-If Analysis
Cummins, Logan
Sommers, Alexander
Mittal, Sudip
Rahimi, Shahram
Seale, Maria
Jaboure, Joseph
Arnold, Thomas
Machine Learning
Artificial Intelligence
Human-Computer Interaction
There exists three main areas of study inside of the field of predictive maintenance: anomaly detection, fault diagnosis, and remaining useful life prediction. Notably, anomaly detection alerts the stakeholder that an anomaly is occurring. This raises two fundamental questions: what is causing the fault and how can we fix it? Inside of the field of explainable artificial intelligence, counterfactual explanations can give that information in the form of what changes to make to put the data point into the opposing class, in this case "healthy". The suggestions are not always actionable which may raise the interest in asking "what if we do this instead?" In this work, we provide a proof of concept for utilizing counterfactual explanations as what-if analysis. We perform this on the PRONOSTIA dataset with a temporal convolutional network as the anomaly detector. Our method presents the counterfactuals in the form of a what-if analysis for this base problem to inspire future work for more complex systems and scenarios.
title Explainable Anomaly Detection: Counterfactual driven What-If Analysis
topic Machine Learning
Artificial Intelligence
Human-Computer Interaction
url https://arxiv.org/abs/2408.11935