Research on Influencing Factors of Regional Taxation Based on ANN-RBF Algorithm

Abstract

Taxation is an important part of national fiscal revenue and an important means for the government to regulate the macroeconomy and maintain stable economic growth. With the development of the economy, taxation is also increasing accordingly. Studying the influencing factors of taxation can better formulate tax policies and optimize the structure of economic development. This paper developed a new method, ANN-RBF (artificial neural network-radial basis function). This paper constructs 14 index systems affecting regional fiscal taxation from four aspects: population, national economy, international trade, and investment expenditure. R² (coefficient of determination) and MSE (mean square error are set as algorithm test indicators. By calculating the contribution of independent variables to taxation, the core factors affecting taxation are analyzed. Finally, the Anhui Province of China is taken as the research object. The results show that: When the number of neurons is 14, the accuracy converges to the maximum. From the contribution analysis, it can be found that the total exports, the secondary industry GDP, the tertiary industry GDP, and the total investment in fixed assets are the core indicators affecting the tax revenue of Anhui Province. By analyzing the tax influencing factors in Anhui Province, this study can provide suggestions for the government to adjust tax revenue and promote economic development.