Exathlon: A Benchmark for Explainable Anomaly Detection over Time Series - Inria - Institut national de recherche en sciences et technologies du numérique Access content directly
Journal Articles Proceedings of the VLDB Endowment (PVLDB) Year : 2021

Exathlon: A Benchmark for Explainable Anomaly Detection over Time Series

Abstract

Access to high-quality data repositories and benchmarks have been instrumental in advancing the state of the art in many experimental research domains. While advanced analytics tasks over time series data have been gaining lots of attention, lack of such community resources severely limits scientific progress. In this paper, we present Exathlon, the first comprehensive public benchmark for explainable anomaly detection over high-dimensional time series data. Exathlon has been systematically constructed based on real data traces from repeated executions of large-scale stream processing jobs on an Apache Spark cluster. Some of these executions were intentionally disturbed by introducing instances of six different types of anomalous events (e.g., misbehaving inputs, resource contention, process failures). For each of the anomaly instances, ground truth labels for the root cause interval as well as those for the extended effect interval are provided, supporting the development and evaluation of a wide range of anomaly detection (AD) and explanation discovery (ED) tasks. We demonstrate the practical utility of Exathlon's dataset, evaluation methodology, and end-toend data science pipeline design through an experimental study with three state-of-the-art AD and ED techniques.
Fichier principal
Vignette du fichier
exathlon.pdf (1.42 Mo) Télécharger le fichier
Origin Files produced by the author(s)

Dates and versions

hal-03381732 , version 1 (17-10-2021)

Identifiers

  • HAL Id : hal-03381732 , version 1

Cite

Vincent Jacob, Fei Song, Arnaud Stiegler, Bijan Rad, Yanlei Diao, et al.. Exathlon: A Benchmark for Explainable Anomaly Detection over Time Series. Proceedings of the VLDB Endowment (PVLDB), 2021. ⟨hal-03381732⟩
127 View
173 Download

Share

Gmail Mastodon Facebook X LinkedIn More