EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

A comprehensive study of machine learning techniques for log-based anomaly detection

Shan Ali iD, Chaima Boufaied, Domenico Bianculli, Paula Branco, Lionel Briand

Empirical Software Engineering · 2025-09 · 30 (5)

DOI: 10.1007/s10664-025-10669-3 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Empirical Software Engineering, online erschienen am 23.06.2025. Verfasst von Shan Ali und 4 weiteren Autor:innen. Beteiligte Einrichtung: University of Ottawa, Ottawa, Canada. Die Arbeit wurde bisher 26-mal zitiert (Crossref) und nennt 89 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: Canada Research Chairs, Natural Sciences and Engineering Research Council of Canada, Mitacs.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Growth in system complexity increases the need for automated techniques dedicated to different log analysis tasks such as Log-based Anomaly Detection (LAD). The latter has been widely addressed in the literature, mostly by means of a variety of deep learning techniques. However, despite their many advantages, that focus on deep learning techniques is somewhat arbitrary as traditional Machine Learning (ML) techniques may perform well in many cases, depending on the context and datasets. In the same vein, semi-supervised techniques deserve the same attention as supervised techniques since the former have clear practical advantages. Further, current evaluations mostly rely on the assessment of detection accuracy. However, this is not enough to decide whether or not a specific ML technique is suitable to address the LAD problem in a given context. Other aspects to consider include training and prediction times as well as the sensitivity to hyperparameter tuning, which in practice matters to engineers. In this paper, we present a comprehensive empirical study, in which we evaluate a wide array of supervised and semi-supervised, traditional and deep ML techniques w.r.t. four evaluation criteria: detection accuracy, time performance, sensitivity of detection accuracy and time performance to hyperparameter tuning. Our goal is to provide much stronger and comprehensive evidence regarding the relative advantages and drawbacks of alternative techniques for LAD. The experimental results show that supervised traditional and deep ML techniques fare similarly in terms of their detection accuracy and prediction time on most of the benchmark datasets considered in our study. Moreover, overall, sensitivity analysis to hyperparameter tuning with respect to detection accuracy shows that supervised traditional ML techniques are less sensitive than deep learning techniques. Further, semi-supervised techniques yield significantly worse detection accuracy than supervised techniques.

Schlagwörter

Stichwörter der Autor:innen

Anomaly detectionDeep learningLogMachine learning

Autor:innen und Institutionen

  • University of Ottawa, Ottawa, Canada.
  • Prince Sultan University, Riyadh, Saudi Arabia.
  • University of Luxembourg, Esch-sur-Alzette, Luxembourg.
  • Research Ireland Lero Centre, University of Limerick, Limerick, Ireland.

ORCID-Profile: Shan Ali

Förderung

  • Canada Research Chairs
  • Natural Sciences and Engineering Research Council of Canada
  • Mitacs

Zitieren

APA

Ali, S., Boufaied, C., Bianculli, D., Branco, P., & Briand, L. (2025). A comprehensive study of machine learning techniques for log-based anomaly detection. Empirical Software Engineering, 30(5). https://doi.org/10.1007/s10664-025-10669-3

Vancouver

Ali S, Boufaied C, Bianculli D, Branco P, Briand L. A comprehensive study of machine learning techniques for log-based anomaly detection. Empirical Software Engineering. 2025;30(5). doi:10.1007/s10664-025-10669-3

BibTeX
@article{Ali2025,
  author = {Ali, Shan and Boufaied, Chaima and Bianculli, Domenico and Branco, Paula and Briand, Lionel},
  title = {A comprehensive study of machine learning techniques for log-based anomaly detection},
  journal = {Empirical Software Engineering},
  year = {2025},
  volume = {30},
  number = {5},
  doi = {10.1007/s10664-025-10669-3}
}
Kostenlos starten →