AI-Powered Real-Time Budget Intelligence Systems For Dynamic Resource Allocation
Аннотация
With the continuous development of artificial intelligence technologies, budget automation has become one of the important ways of modern financial governance, and the demand for real-time allocation is also increasing. Expenditure estimation plays a very important role in the field of public resource management. This paper proposes an AI-powered system that deals with the dynamic budget allocation problem in the way of intelligent decision modeling. This work focuses on resource optimization by a data-driven framework as part of fiscal transformation strategies to improve transparency. Through combining the current prioritization models of budget planning, an interactive decision system is built by AHP and regression, to facilitate the sharing of fiscal intelligence through the continuous development of new technologies, such as correlation analysis, and improve the accuracy and agility of allocation systems. Based on empirical evaluation, the interaction of fiscal responsiveness and decision latency in maximizing utilization and, therefore, resilience for governments and flexibility for coordination between a central authority and local agencies is analyzed. The experimental results on Uzbekistan's cross-sectional budget data and simulated fiscal stress scenarios demonstrate the feasibility and scalability of the proposed model. The results showed that while correlation-driven prioritization could be a useful strategy because of its predictive accuracy via linear estimations for budgetary needs and similar project pipelines, regression weakens the performance of the allocation framework with significantly volatile indicators; it is ineffective in rapid-response conditions. Finally, policy suggestions and technical directions are given. The conclusion also reinforces the robustness and applicability of AHP-based systems and regression tools.