Predictive analytics for enhancing public finance management efficiency

Abstract

The article examines the use of predictive analytics to enhance the effectiveness of public finance management in the context of dynamic economic changes. The relevance of the study is driven by the need to improve budgeting processes, expenditure control, and strategic decision-making based on predictive data.

The aim of the study is to assess the potential of predictive analytics for improving public finance management and to justify scientific and practical recommendations for implementing analytical platforms to increase the transparency of financial processes and strengthen control over budget flows. To achieve this goal, the study employed methods of system analysis, comparative research, and modeling. An analysis of modern approaches to building analytical models, such as regression models, decision trees, neural networks, and cluster analysis, was conducted. It was found that the effectiveness of these methods depends on the quality of input data, the technological infrastructure of institutions, and the level of digital competence of personnel.

During the study, an algorithm for applying predictive models was developed, covering the stages of data collection, processing, and cleaning, selecting the optimal model, training algorithms, and evaluating forecast accuracy. It has been proven that implementing this algorithm improves the justification of managerial decisions and reduces the risks of budget overruns. Particular attention is paid to cybersecurity issues and the creation of multi-level data protection to prevent information leaks.

The conclusions indicate that predictive analytics is an effective tool for optimizing public financial management, ensuring the flexibility and transparency of budgeting processes. Recommendations are proposed regarding the creation of integrated analytical platforms with multi-scenario analysis functions, the development of training programs to improve the digital competence of employees, and the implementation of pilot projects to assess forecasting efficiency in real-world conditions.