From Data to Prediction: A Study on China’s GDP Forecasting

Abstract

This study utilizes the Least Absolute Shrinkage and Selection Operator (LASSO) regression model, implemented through the R programming language, to refine GDP forecasting methods in China. The analysis centers on the function of the three main monetary indicators—M0, M1, and M2—using time-series data from reliable sources, including the People’s Bank of China and the National Bureau of Statistics. These variables have been identified as significant drivers of GDP fluctuations. By leveraging LASSO’s ability to select relevant variables and control for overfitting, the model achieves a streamlined and accurate approach to real-time economic forecasting. The results highlight the importance of money supply factors in predicting GDP and emphasize the LASSO model’s efficiency in enhancing traditional forecasting techniques. Furthermore, this study offers valuable insights for policymakers and business strategists, who may use these findings to guide economic planning. Integrating modern statistical methods with classical economic models, this research also paves the way for future exploration into global economic forecasting.