Ensemble Modeling for Economic Projections: The Guangdong-Hong Kong-Macao Greater Bay Area
Abstract
This study aims to construct a multi-model integrated forecasting framework to systematically analyze and predict the economic development of the Guangdong-Hong Kong-Macao Greater Bay Area over the next 5–10 years. First, by collecting multi-dimensional data encompassing demographics, technology, industry, and economy, key factors influencing economic development will be identifi ed. Next, the CRITIC Weighting Method will be employed to quantify the impact of these factors and screen core variables. On this basis, both Random Forest Regression Model and Time Series Analysis (ARIMA) Model will be established to conduct multi-perspective predictions and validation of regional economic trends. Finally, based on the model outcomes, policy recommendations will be proposed to promote high-quality economic development in the Guangdong-Hong Kong-Macao Greater Bay Area, providing a scientific foundation for regional development strategies.
Keywords
CRITIC weighting method; Random Forest Regression; Time Series Analysis (ARIMA); Econometric Models; Machine Learning Regression
Full Text:
PDFReferences
[1] Diakoulaki, D., Mavrotas, G., & Papayannakis, L. (1995). Determining objective weights in multiple criteria problems: The critic method. Computers & Operations Research, 22(7), 763–770. https://doi.org/10.1016/0305-0548(94)00059-H
[2] Breiman, L. (2001). Random Forests. Machine Learning, 45(1), 5–32.
[3] Janacek, G. (2019). Time Series Analysis Forecasting and Control. Journal of Time Series Analysis. https://doi.org/10.1111/j.1467-9892.2009.00643.x
DOI: http://dx.doi.org/10.18686/ahe.v9i5.14266
Refbacks
- There are currently no refbacks.
