Artificial Intelligence Integrated MIS Framework for Proactive Cyber Threat Intelligence and Organizational Security Resilience

Abstract

Organizations increasingly deploy artificial intelligence, cyber threat intelligence, automated security tools, and Management Information Systems, yet fragmented security information and predominantly reactive processes can limit proactive threat management and organizational resilience. This study aimed to develop and empirically evaluate an Artificial Intelligence Integrated MIS Framework linking intelligent cybersecurity capabilities with proactive cyber threat management and organizational security resilience. A quantitative, cross-sectional, multiple-case-based design was employed using approximately 300 valid professional responses representing enterprise, cloud-enabled, financial-services, telecommunications, manufacturing, healthcare, and other data-intensive organizational cases. The principal variables were AI-Enabled Threat Detection, Cyber Threat Intelligence Integration, MIS Security Information Integration, Automated Threat Response, Predictive Cyber Risk Analytics, Proactive Cyber Threat Management, and Organizational Security Resilience. Data analysis incorporated descriptive statistics, Cronbach’s alpha, Kaiser-Meyer-Olkin assessment, Bartlett’s test, Pearson correlation, ordinary least-squares multiple regression, variance inflation factors, tolerance, Durbin-Watson statistics, and residual diagnostics. Findings showed high construct means ranging from 3.91 for Automated Threat Response to 4.14 for Organizational Security Resilience, with overall instrument reliability of α = 0.93 and KMO = 0.884. Correlations between the five AI-integrated MIS capabilities and proactive threat management ranged from r = .54 to r = .72, with Predictive Cyber Risk Analytics showing the strongest association. The first regression model explained 63.8% of PCTM variance, R² = .638, adjusted R² = .631, F (5,294) = 103.63, p < .001. The second model explained 68.4% of Organizational Security Resilience variance, R² = .684, adjusted R² = .677, F (6,293) = 105.70, p < .001, with Proactive Cyber Threat Management producing the strongest effect, β = .38, p < .001. The findings imply that coordinated AI detection, threat intelligence, MIS integration, predictive analytics, and automated response can strengthen proactive cybersecurity decision-making, adaptive defense, continuity, recovery, and organizational security resilience.