The Impact of Tax Revenues and Revaluation Rates on Poverty in Türkiye: Artificial Neural Network Approach

The main objective of this study is to analyze the relationship between poverty, total tax revenues and revaluation rates, which indicate the increase rates of some fixed taxes each year and to test the effect of total tax revenues and revaluation rates on poverty between 1991 and 2021 in Türkiye. In this framework, income poverty data calculated by us based on per capita income data using the Hodrick-Presscot filter is used in this study. The relationship between the variables are tested with the artificial neural network method, which is used to obtain more realistic and resistant results, unlike the time series models used in the economic literature recently. Therefore, according to the weight values obtained from the output data in the 4-layer and 7-neuron artificial neural network model, it is concluded that a 1% increase in total tax revenues increases income poverty by 1.20% and a 1% increase in revaluation rates increases income poverty by 0.61%.