Revisión sistemática sobre identificación de anomalías en el consumo de servicios web masivos mediante técnicas de machine learning
Abstract
This paper provides a systematic literature review on the application of machine learning techniques for anomaly detection within web services and distributed systems. Our methodology involved structured queries across major academic databases, including IEEE Xplore, Scopus, ScienceDirect, and the ACM Digital Library, covering research published between 2021 and 2025. Following the application of rigorous inclusion and exclusion criteria, a final cohort of 50 relevant articles was selected for detailed analysis. These studies were categorized based on data types, learning paradigms, application domains, and evaluation metrics to pinpoint current trends, strengths, and inherent limitations in the field. Our findings highlight a clear shift toward hybrid models and deep learning architectures, alongside a growing emphasis on explainability and scalability in distributed environments.
Fields of Study & Subjects
Anomaly Detection Techniques and Applications
Network Security and Intrusion Detection
Software System Performance and Reliability
Publication details
- Journal / source
- REVISTA COLOMBIANA DE TECNOLOGIAS DE AVANZADA
- Publisher
- Universidad de Pamplona
- Volume
- 1
- Issue
- 47
- Pages
- 209–218
- Publication date
- 9 February 2026
- Language
- ES