AI-Driven Economic Forecasting Framework for Predicting Market Dynamics and Financial Trends

Authors

  • João Silva
  • Inês Costa

DOI:

https://doi.org/10.71086/IAJE/V13I2/IAJE1307

Keywords:

Tax Progressivity, Income Inequality, OECD Countries, Gini Coefficient, Tax Progressivity Index, Social Spending, Economic Policy.

Abstract

 The existing paper is centered around the effect that the introduction of tax progressivity reforms can have on income inequality in the OECD countries on the basis of statistical analysis in order to establish the relationship between Tax Progressivity Index and Gini coefficient from 1990 to 2020. To conduct statistical analysis, the paper ensures that such factors as GDP per capita, unemployment rates, and social spending, among others, will be controlled through the use of panel data regression models. As a result, the short run and long run effects of tax reforms on the inequality of income will be determined. The findings imply that there exists a statistically significant (negative) correlation between tax progressivity and income inequality, and more tax progressivity (higher Kakwani index) is linked to less inequality of income in the country. Moreover, such an effect varies depending on the country, with the effect of tax progressivity and social spending being greater in such countries as Sweden and Denmark. On the contrary, there exist weak relationships between tax progressivity and inequality in countries like the United States with little social expenditure. The research also implies that the effect of the reforms is lagged, with the rise in inequality being noted after several years after reforms were introduced. The implications of these findings are that long-term policy plans involving tax progressivity and social expenditure are important in attaining large decreases in income inequality. The test was conducted at the 5% level of statistical significance, and the strength of the results was checked by strong checks through the use of alternative model specifications.

Downloads

Published

2026-06-30

Issue

Section

Articles

How to Cite

Silva, J., & Costa, I. (2026). AI-Driven Economic Forecasting Framework for Predicting Market Dynamics and Financial Trends. International Academic Journal of Economics, 13(2), 1-8. https://doi.org/10.71086/IAJE/V13I2/IAJE1307