Answers are grounded in this paper and cite their sources.
Study forecasts unemployment and inflation in China, suggesting improved accuracy with machine learning.
This study forecasts China's CPI inflation and urban registered unemployment rate using both Ordinary Least Squares (OLS) and Extreme Gradient Boosting (XGBoost) models. Based on annual macroeconomic and monetary data, OLS serves as a linear benchmark capturing trend and persistence, while XGBoost accommodates nonlinearities and variable interactions.A comparative evaluation of in-sample estimation and out-of-sample forecasting performance shows that machine learning improves predictive accuracy, particularly for unemployment, while OLS provides transparent economic interpretation.The results suggest that integrating econometric and machine learning approaches enhances macroeconomic forecasting in China.
No takes yet. Share an insight, caveat, or question.
Ting Yangxian (2026) studied this question.
Synapse has enriched 10 related papers. Consider them for comparative context: