Intellectualization of public sector financial resource management: analytical tools and efficiency models

Abstract

The study examines the intellectualization of public financial management through the integration of Big Data, machine learning, and graph neural networks. These tools enable proactive risk forecasting, improve budget accuracy, and enhance real-time anomaly detection, forming a new paradigm of fiscal transparency, discipline, and strategic efficiency.

Problem statement. Traditional public finance management approaches no longer meet the demands of fiscal complexity and transparency, requiring the adoption of intelligent models based on Big Data, machine learning, and graph neural networks to enable proactive risk forecasting and improve budgeting efficiency.

Unresolved aspects of the problem. Key challenges in intelligent public finance management include the lack of an integrated AI model, “black box” transparency issues, outdated IT systems, poor data quality, and insufficient institutional capacity, revealing critical knowledge gaps for further research.

Purpose of the article. The article aims to scientifically justify and develop methodological foundations for the intellectualization of public financial management to address identified systemic challenges and gaps.

Presentation of the main material. The article develops a conceptual framework for intellectualized public financial management, integrating GNNs for anomaly detection and ML for accurate budget forecasting across the fiscal cycle. Explainable AI principles ensure transparency, complemented by strategic recommendations for IT modernization, data quality, and digital competency development.

Conclusions. The study proposes a new paradigm of public finance efficiency through analytical integration, algorithmic forecasting, and transparency, with the Intelligent Financial Governance model enabling modernization, digital audit, and risk-based monitoring to enhance fiscal stability and long-term economic resilience.