Prediction of Urban Talent Flow and Economic Growth Based on Random Forest Model

To explore the non-linear relationship between urban human resource mobility and economic growth, we conducted an in-depth study of the patterns of dynamic change in China's urban labor market. Taking the Yangtze River Delta, the Pearl River Delta and the Beijing-Tianjin-Hebei region as examples, an empirical study was conducted on human resource mobility and economic development for the period 2018-2023. A new method based on multidimensional data fusion is proposed: taking migrant inflow and outflow rates and the GDP growth rate as indicators, the decision tree synergy method is used to analyze complex migrant flow variables. The experimental results show that the method has an average error of 4.12 in the training samples and 5.56 in the test samples, and that the prediction accuracy varies between 94.30% and 91.20%. The results show that the random forest model can effectively reveal regional economic dynamics, optimize the allocation of political resources and provide technical support and theoretical knowledge to improve the competitiveness of urban agglomerations.