Economic forecast of Guangdong-Hong Kong-Macao Greater Bay Area

Empirical analysis based on PCA-ARIMA-LSTM mixed model

Abstract

This study presents an innovative framework for analyzing and forecasting economic development in the Guangdong-Hong Kong-Macao Greater Bay Area (GBA), a key driver of China's economic growth. The research makes three significant contributions: First, it develops a novel multi-method analytical approach combining multiple linear regression, Granger causality tests, and principal component analysis (PCA) to systematically identify the most influential growth factors - particularly highlighting logistics networks and technological inputs as critical leverage points for policy intervention. Second, the study pioneers a hybrid modeling strategy that integrates ARIMA and LSTM techniques, demonstrating superior predictive performance for the GBA's 5-10 year economic trajectory. Third, the findings provide actionable insights for policymakers, suggesting that targeted investments in technology infrastructure and logistics optimization can accelerate regional development while offering a replicable model for other emerging mega-regions. The proposed framework not only enhances understanding of the GBA's growth dynamics but also establishes a new benchmark for regional economic analysis.