Department of Computer Science, Yaba College of Technology, Lagos, Nigeria.
School of Computer Science, University of Hertfordshire, Hartfield, United Kingdom.
Aberdeen Business School, Robert Gordon University, Aberdeen, United Kingdom.
EGTL, Chevron Nigeria Limited, Nigeria.
Research Article
World Journal of Advanced Research and Reviews, 2020, 08(02), 369-376
Article DOI: 10.30574/wjarr.2020.8.2.0425
Received on 11 November 2020; revised on 20 November 2020; accepted on 21 November 2020
This comparison between Machine Learning Models and Behavioral Analytics concerning mitigation time further stresses the critical importance of each towards an increase in cybersecurity. Finally, Machine Learning Models continue doing great despite minimum mitigation times for high efficacy of detection; therefore, the position is favorable for a prompt response in case there are threats to occur. While behavioral analytics does well in certain contexts, it is unpredictable due to outside factors and requires further optimization to make the results consistent. Real-time monitoring ensures continuity in performance and shows adaptability to rapidly changing hazards, while anomaly detection focuses on finding unusual and complicated threats, especially in dynamic environments. These approaches, put together, can substantially strengthen cybersecurity frameworks. Machine learning models provide a solid backbone for speed, while behavioral analytics delivers substantial insight into user behavior. Real-time monitoring ensures constant monitoring, while anomaly detection fortifies the barriers against complex threats. Indeed, all organizations must have an all-inclusive approach to strategic integration, contextual flexibility, continuous evaluation, and investment in innovation to maximize such benefits. By incorporating these operations with workforce development and advanced technologies, proactive and resilient cybersecurity frameworks can be achieved. In fact, only such comprehensive frameworks can protect the assets of organizations and ensure continuity of operations in an ever-evolving threat landscape.
Cybersecurity; Data Analytics; Predictive Analytics; Risk Mitigation; Threat Forecasting; Threat Detection
Preview Article PDF
Daniel Kashetu Alasa. Harnessing predictive analytics in cybersecurity: Proactive strategies for organizational threat mitigation. World Journal of Advanced Research and Reviews, 2020, 8(2), 369-376. Article DOI: https://doi.org/10.30574/wjarr.2020.8.2.0425