Enhancing Institutional Cybersecurity through Intelligent Predictive Analytics for Phishing Attack Detection (Published)
The rapid digitalization of institutional operations has increased exposure to cyber threats, particularly phishing attacks that exploit human and system vulnerabilities. Traditional security mechanisms often fail to detect evolving phishing techniques due to their static and reactive nature. This study presents an intelligent predictive analytics framework designed to enhance institutional cyber resilience through proactive phishing attack detection. Using a dataset of 2,200 labeled web-based interaction records, the study applied supervised machine learning techniques to identify malicious patterns indicative of phishing activities. Two predictive models; Random Forest (RF) and Support Vector Machine (SVM) were developed and evaluated using standard performance metrics including accuracy, precision, recall, and F1-score. Experimental results reveal that the Random Forest model achieved superior predictive performance, recording an accuracy of 95.7%, while SVM achieved 93.3%. The findings demonstrate that predictive analytics can significantly strengthen institutional cybersecurity by improving early threat detection, minimizing false positives, and enhancing overall system resilience. This study contributes to cybersecurity research by providing a scalable, data-driven framework suitable for deployment in institutional environments seeking proactive phishing mitigation strategies.
Keywords: cyber resilience, institutional cybersecurity, machine learning, phishing detection, predictive analytics, random forest (RF), support vector machine (SVM)