Integrating Real-Time Business Intelligence Dashboards with AI-Driven Predictive Threat Analytics for Scalable Cybersecurity Incident Management in U.S. Enterprise Cloud Environments

• Abilly Elly

  Texas University

  Author

The rapid migration of U.S. enterprises to cloud infrastructures has created an expanded attack surface that traditional, reactive cybersecurity measures cannot adequately protect. While Business Intelligence (BI) tools and AI-driven analytics have separately advanced threat detection, a validated framework integrating real-time BI dashboards with predictive threat analytics for scalable incident management in enterprise cloud environments remains absent from the literature. This study addresses this gap by proposing a hybrid framework that combines interactive BI dashboards with machine learning-based predictive threat analytics, built upon the NIST CSF 2.0 Govern-Identify-Protect-Detect-Respond-Recover functions. Employing a design-based research methodology incorporating retrospective analysis of security telemetry from 150 enterprise cloud environments and prospective simulation of AI-driven attack scenarios, the framework was validated against static-rule and standalone AI approaches. Key findings demonstrate that the integrated framework achieved an 89.4% accuracy in threat prediction, reduced Mean Time to Detect (MTTD) by 54% (from 28 days to 13 days), and cut Mean Time to Respond (MTTR) by 47%, outperforming baseline methods. The main conclusion is that the real-time BI-AI integration provides a replicable, scalable model for proactive cloud security operations. Practical implications include a reference architecture for security teams and policy guidance for aligning incident response with emerging regulatory expectations (Bhuiyan et al., 2026; Ankhi, 2025).

• pdf

Copyright (c) 2026 Abilly Elly (Author)

This work is licensed under a Creative Commons Attribution 4.0 International License.