AI-Augmented Security Operations Centers: Predictive Threat Prioritization Using Business Impact Modeling and Machine Learning
The American Journal of Engineering and Technology · 06.06.2026 · 08 (06) · 79-104
DOI: 10.37547/tajet/volume08issue06-04 ↗Kurz gefasst
Fachartikel in der Zeitschrift The American Journal of Engineering and Technology, online erschienen am 06.06.2026. Verfasst von MD Al-Amin Chowdhury und 3 weiteren Autor:innen.
Abstract (Originalsprache)
The increasingly quick growth in the amount, speed, and complexity of cyber threats has placed a great deal of strain on the operational performance of contemporary Security Operations Centers (SOCs), where analysts frequently must deal with a large volume of alerts and have few contextual prioritization tools at their disposal. The rule-based and Security Information and Event Management (SIEM)-based systems though successful in detection often fail to match the threat response with the organizational risk exposure and hence allocate resources optimally and take a long time to respond to incidents. Within the framework of this research, the authors suggest a threat detection approach using machine learning and business impact modeling with the help of AI to offer predictive and context-centered threat prioritization. Based on publicly available cybersecurity datasets, including CICIDS2017 and UNSW-NB15, various supervised learning models, including Random Forest, Extreme Gradient Boosting (XGBoost), and Logistic Regression, were trained and assessed. A quantitative business impact scoring mechanism based on criticality of assets, operational dependency, and potential financial loss was integrated with these models. The hybrid model suggested above produces a composite prioritization score that indicates the probability of a threat and its possible business impact. Empirical evidence shows that the combined method is much more accurate at prioritization, with greater precision and F1-scores than single machine learning models, and lower mean time to detect (MTTD) and mean time to respond (MTTR). The results underscore the importance of inculcating business conditions into AI-based cybersecurity systems. This work is relevant to the development of intelligent SOC design, as it fills the gap between technical threat detection and the organizational risk management by providing a scalable, data-driven solution to improving cyber resilience in complex enterprise settings.
Zitieren
APA
Chowdhury, M. A., Rashid, H. U., Afroz, S., & Das, S. R. (2026). AI-Augmented Security Operations Centers: Predictive Threat Prioritization Using Business Impact Modeling and Machine Learning. The American Journal of Engineering and Technology, 08(06), 79-104. https://doi.org/10.37547/tajet/volume08issue06-04
Vancouver
Chowdhury MA, Rashid HU, Afroz S, Das SR. AI-Augmented Security Operations Centers: Predictive Threat Prioritization Using Business Impact Modeling and Machine Learning. The American Journal of Engineering and Technology. 2026;08(06):79-104. doi:10.37547/tajet/volume08issue06-04
BibTeX
@article{Chowdhury2026,
author = {Chowdhury, MD Al-Amin and Rashid, Hasib Ur and Afroz, Sadia and Das, Shuvo Ranjan},
title = {AI-Augmented Security Operations Centers: Predictive Threat Prioritization Using Business Impact Modeling and Machine Learning},
journal = {The American Journal of Engineering and Technology},
year = {2026},
volume = {08},
number = {06},
pages = {79--104},
doi = {10.37547/tajet/volume08issue06-04}
}
EUVIMED