Treffer: Impact of economic indicators on national income

[ABSTRACT ONLY; NO FULL TEXT] This study employs advanced machine learning methodologies to investigate the predictive relationships between key economic variables and high-income country classification, leveraging datasets from the World Data Bank covering all countries from 2021 to 2023. The analysis focuses on five critical indicators: Gross Domestic Product (GDP), GDP growth, foreign investment, inflation rate, and government spending, examining their influence on economic performance and national income levels. The research is structured around descriptive and predictive analytics objectives. Descriptive analytics aim to examine GDP, GDP growth, foreign investment, inflation rate, and government spending across various countries. It also seeks to analyze and summarize relationships between these economic indicators and national income levels, providing foundational insights into economic trends and their implications. Predictive analytics focus on developing machine learning models that accurately predict whether a country is classified as high-income, while evaluating and comparing the effectiveness of algorithms, including logistic regression, decision trees, random forests, XGBoost, and neural networks, in forecasting high-income status. The investigation addresses several key research topics: changes in GDP and income level distributions between 2021 and 2023; differences in GDP growth across income levels; significant economic indicators predicting high-income countries; the collective impact of foreign investment, government spending, and inflation on GDP; and the comparative performance of neural networks versus traditional models in identifying significant indicators. Python's powerful libraries for data visualization and analysis are employed to clean, extract, and explore datasets systematically, enabling the development of models that uncover patterns, relationships, and trends in economic performance. The anticipated findings aim to identify the most reliable predictive models and highlight the ...