Skip to content
Open access

An Intelligent AI-Driven Decision Support Framework for Optimizing Strategic Management and Resource Allocation in Complex Digital Systems

Sep 2026 · Computer and Decision Making: An International Journal · 0 citations

Abstract

Efficient resource allocation is essential for maintaining performance, cost efficiency, and responsiveness in complex digital systems. This study developed an intelligent AI-driven decision-support framework for predicting scale-up, scale-down, and no-action resource-allocation decisions from operational and infrastructure characteristics. A dataset comprising 1,000 observations was analyzed using descriptive statistics, inferential testing, machine-learning classification, sensitivity assessment, and explainable AI. Logistic Regression, Random Forest, and Gradient Boosting were comparatively evaluated using stratified cross-validation and held-out testing. Gradient Boosting demonstrated the strongest performance and, following hyperparameter optimization, achieved 99.5% test accuracy, 96.67% balanced accuracy, and a macro-F1 score of 0.9812. Significant differences among allocation states were observed for CPU usage, memory usage, utilization, throughput, and latency, whereas cloud provider, region, and virtual-machine type showed limited association with allocation outcomes. Explainability analysis identified CPU usage (53.33%) and memory usage (46.66%) as the dominant predictive determinants. Sensitivity analysis further demonstrated that performance remained stable after removing highly correlated operational indicators. The findings establish a transparent and computationally effective framework for transforming operational telemetry into resource-allocation recommendations, providing a foundation for data-driven capacity planning and strategic digital resource management.

Read PDF

We use cookies to run the site and, with your consent, for analytics and to show ads. See our Cookie Policy.