Copyright © 2026 Authors retain the copyright of this article. This article is an open access article distributed under the Creative Commons Attribution License which permits unrestricted use, distribution, and reproduction in any medium, provided the original work is properly cited.

@article{200402,
        author = {Ms. Khushi Chudasama and Mr. Prakash Patel and Mr. Mukesh Parmar and Ms. Shreya Patel},
        title = {An Efficient Machine Learning Approach for Anomaly Detection in Web Server Logs using Isolation Forest},
        journal = {International Journal of Innovative Research in Technology},
        year = {2026},
        volume = {12},
        number = {12},
        pages = {3611-3615},
        issn = {2349-6002},
        url = {https://ijirt.org/article?manuscript=200402},
        abstract = {This paper presents a machine learning-based approach for anomaly detection in web server logs using the Isolation Forest algorithm. With the rapid growth of web applications, analyzing large volumes of log data manually has become inefficient and error-prone. To address this challenge, the proposed system converts raw Nginx server logs into a structured format, followed by preprocessing and feature engineering to extract meaningful attributes.
An unsupervised learning model based on Isolation Forest is applied to detect anomalous patterns in user requests and server responses. The model is evaluated on a dataset containing 10,000 log entries, where it successfully identifies approximately 8% of the records as anomalous. The model’s performance is evaluated using metrics such as precision, recall, and F1-score, along with an analysis of how anomalies are distributed within the dataset.
The results demonstrate that the proposed approach can efficiently detect unusual behavior in web traffic and reduce manual effort in log analysis. This method can be further extended for real-time monitoring and enhanced cybersecurity applications.},
        keywords = {Anomaly Detection, Isolation Forest, Web Server Logs, Machine Learning, Cybersecurity, Log Analysis},
        month = {May},
        }