Guardado en:
Detalles Bibliográficos
Autores principales: Zan, Lei, Assaad, Charles K., Devijver, Emilie, Gaussier, Eric, Aït-Bachir, Ali
Formato: Preprint
Publicado: 2024
Materias:
Acceso en línea:https://arxiv.org/abs/2402.06500
Etiquetas: Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
_version_ 1866929439314542592
author Zan, Lei
Assaad, Charles K.
Devijver, Emilie
Gaussier, Eric
Aït-Bachir, Ali
author_facet Zan, Lei
Assaad, Charles K.
Devijver, Emilie
Gaussier, Eric
Aït-Bachir, Ali
contents This paper introduces a new structural causal model tailored for representing threshold-based IT systems and presents a new algorithm designed to rapidly detect root causes of anomalies in such systems. When root causes are not causally related, the method is proven to be correct; while an extension is proposed based on the intervention of an agent to relax this assumption. Our algorithm and its agent-based extension leverage causal discovery from offline data and engage in subgraph traversal when encountering new anomalies in online data. Our extensive experiments demonstrate the superior performance of our methods, even when applied to data generated from alternative structural causal models or real IT monitoring data.
format Preprint
id arxiv_https___arxiv_org_abs_2402_06500
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle On the Fly Detection of Root Causes from Observed Data with Application to IT Systems
Zan, Lei
Assaad, Charles K.
Devijver, Emilie
Gaussier, Eric
Aït-Bachir, Ali
Artificial Intelligence
This paper introduces a new structural causal model tailored for representing threshold-based IT systems and presents a new algorithm designed to rapidly detect root causes of anomalies in such systems. When root causes are not causally related, the method is proven to be correct; while an extension is proposed based on the intervention of an agent to relax this assumption. Our algorithm and its agent-based extension leverage causal discovery from offline data and engage in subgraph traversal when encountering new anomalies in online data. Our extensive experiments demonstrate the superior performance of our methods, even when applied to data generated from alternative structural causal models or real IT monitoring data.
title On the Fly Detection of Root Causes from Observed Data with Application to IT Systems
topic Artificial Intelligence
url https://arxiv.org/abs/2402.06500