Income Prediction Based on Personal Attributes: Comparing Machine Learning Models

This research investigates the factors influencing income levels using machine learning techniques. Based on a dataset of 48,842 individuals, the study employs LightGBM, Random Forest, and K-Nearest Neighbors algorithms to predict annual income. The results demonstrate that LightGBM achieved the highest accuracy, exceeding 90%. Feature importance analysis revealed age as the most significant predictor of income. This study provides valuable insights into the factors that contribute to income inequality and has potential implications for policy development and social research. By understanding the key determinants of income, policymakers can develop targeted interventions to address income disparities and promote social equity.