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{199348,
        author = {G Venkatesh and G.Pavan Kalyan Reddy and KASU VASUDEVA REDDY and Dr.P.THANGAVEL},
        title = {Network Traffic Analysis Using Machine Learning},
        journal = {International Journal of Innovative Research in Technology},
        year = {2026},
        volume = {12},
        number = {11},
        pages = {12362-12367},
        issn = {2349-6002},
        url = {https://ijirt.org/article?manuscript=199348},
        abstract = {With the rapid expansion of internet usage and network-based applications, effective network traffic analysis has become indispensable for ensuring cybersecurity, performance optimization, and reliable communication. This paper presents a machine learning-based framework for automatically monitoring, classifying, and detecting anomalies in network traffic by analyzing large volumes of historical and real-time data. Multiple supervised algorithms — including Decision Trees, Support Vector Machines (SVM), Random Forest, XGBoost, and Long Short-Term Memory (LSTM) networks — are employed to distinguish normal from anomalous behavior encompassing denial-of-service attacks, intrusion attempts, and malware activities. Features such as packet size, flow duration, protocol type, packet loss rate, and average latency are extracted alongside graph-based topological features including node betweenness centrality and link stability scores. Experimental evaluation on a real-world dataset of 500,000 network event logs demonstrates that the LSTM model achieves 92.7% accuracy with 12 ms inference latency per event. Integration of graph-based features improves overall model accuracy by 6.5% over feature-only baselines. The proposed framework provides superior accuracy, adaptability, and scalability compared to conventional rule-based monitoring approaches.},
        keywords = {Network Traffic Analysis, Machine Learning, Anomaly Detection, Intrusion Detection, SVM, LSTM, XGBoost, Random Forest, Network Security, Supervised Learning, Graph Neural Networks.},
        month = {April},
        }