Abstract

Cybercrime has become a critical challenge in modern digital environments, requiring intelligent detection systems capable of identifying malicious network behaviors with high reliability. This paper presents a machine learning-based approach for cybercrime detection using the Random Forest classifier. The model is trained to distinguish between normal and malicious traffic patterns using numerical network features such as packet size, duration, and data volume. Random Forest leverages bootstrap aggregation and random feature selection to construct an ensemble of decision trees, reducing overfitting and improving generalization. Experimental evaluation is performed on a labeled dataset, demonstrating the model’s ability to learn discriminative patterns through impurity-based split criteria and majority voting for final predictions. Performance analysis is conducted using confusion matrix-based metrics including accuracy, precision, recall, and F1-score. Results show that the proposed model achieves 91% accuracy, 90.2% precision, 92% recall, and a 91.1% F1-score, indicating strong sensitivity to cybercrime activities with low false alarm rates. The findings confirm that Random Forest provides an effective and robust solution for cybercrime detection in network environments and outperforms several traditional machine learning models in balancing detection capability and predictive reliability.

References

• Almansouri, H., Khajah, M., & Alsnayen, N. (2026). Machine learning model for predicting cyber-criminal characteristics. Kuwait Journal of Science, 53(1), 100487. https://doi.org/10.1016/j.kjs.2025.100487
• Genuario, F., Santoro, G., Giliberti, M., Bello, S., Zazzera, E., & Impedovo, D. (2024). Machine Learning-Based Methodologies for Cyber-Attacks and Network Traffic Monitoring: A Review and Insights. Information, 15(11), 741. https://doi.org/10.3390/info15110741
• Madhavi, S., Divyadharshini, D., & Divya, S. (2022). machine learning model to predict cyber attack. International Journal of Health Sciences, 1341–1349. https://doi.org/10.53730/ijhs.v6ns6.9745
• Modi, A., & Navadiya, K. (2025). Anomaly detection in cybersecurity using random forest. International Journal of Advanced Research in Science Communication and Technology, 278–283. https://doi.org/10.48175/ijarsct-23342
• Sampath, Ch. S., & Anuradha, Dr. P. (2023). Intrusion Detection Using Machine Learning: a Random Forest-Based approach. In International Journal for Multidisciplinary Research (IJFMR) (Vol. 5, Issue 3, pp. 1–3). https://www.ijfmr.com/papers/2023/3/3408.pdf
• Burman, R. K., Kumar, A., Kumari, S., Kumar, N., Kumar, B., & Kumar, V. (2025). Machine learning based anomaly detection for network intrusion detection in cyber security. Atlantis Press. https://doi.org/10.2991/978-94-6463-787-8_42
• Arora, T., Sharma, M., & Khatri, S. K. (2019). Detection of Cyber Crime on Social Media using Random Forest Algorithm. 2019 2nd International Conference on Power Energy, Environment and Intelligent Control (PEEIC), 47–51. https://doi.org/10.1109/peeic47157.2019.8976474
• Farnaaz, N., & Jabbar, M. (2016). Random forest modeling for network intrusion detection system. Procedia Computer Science, 89, 213–217. https://doi.org/10.1016/j.procs.2016.06.047
• Machine Learning based Detection of Cyber Crime Hub Analysis using Twitter Data. (2021, September 24). IEEE Conference Publication | IEEE Xplore. https://ieeexplore.ieee.org/document/9573736
• Abdiyeva-Aliyeva, G., Aliyev, J., & Sadigov, U. (2022). Application of classification algorithms of Machine learning in cybersecurity. Procedia Computer Science, 215, 909–919. https://doi.org/10.1016/j.procs.2022.12.093
• Veena, K., Meena, K., Kuppusamy, R., Teekaraman, Y., Angadi, R. V., & Thelkar, A. R. (2022). Cybercrime: Identification and prediction using Machine learning techniques. Computational Intelligence and Neuroscience, 2022, 1–10. https://doi.org/10.1155/2022/8237421
• Jyothirmai, M., Jayalakshmi, M., Ahalya, C., & Kumar, L. L. P. (2025). Cyber crime detection using machine learning. In Lecture notes in electrical engineering (pp. 1525–1535). https://doi.org/10.1007/978-981-95-0269-1_173
• Elluri, L., Mandalapu, V., Vyas, P., & Roy, N. (2023). Recent advancements in machine learning for cybercrime prediction. Journal of Computer Information Systems, 65(2), 249–263. https://doi.org/10.1080/08874417.2023.2270457