Data mining on fiscal data

This bachelor thesis focuses on the application of data mining methods to fiscal data to uncover hidden patterns and correlations that can contribute to a better understanding of economic phenomena and the efficiency of public financing. The work centers on processing data according to the CRISP-DM (Cross-Industry Standard Process for Data Mining) methodology and applying it to real data obtained from public sources. The methodology includes steps such as understanding the data, data preparation, modeling, and evaluation of results. For the analysis, fiscal data from municipalities, including information on the financial status of municipalities, investment expenditures, and property taxes, was utilized. The main goal of the analysis was to determine how changes in fiscal policy affect the investment activities of municipalities. In the modeling phase, association rules and exploratory analysis were employed. The results of the analysis provide valuable insights into the structure of fiscal data and can serve as a basis for further research and decision-making in the public sector.