Multicollinearity Resolution Based on Machine Learning: A Case Study of Carbon Emissions

This study presents a general analytical framework using DBSCAN clustering and penalized regression models to address multifactor problems with structural complexity and multicollinearity issues, such as carbon emission issue. The framework leverages DBSCAN for unsupervised learning to objectively cluster features. Meanwhile, penalized regression considers model complexity control and high dimensional feature selection to identify dominant influencing factors. Applying this framework to analyze energy consumption data for 46 industries from 2000 to 2019 identified 16 categories in the sample of China. We quantitatively assessed emission characteristics and drivers for each. The results demonstrate the framework's analytical approach can identify primary emission sources by category, providing quantitative references for decision-making. Overall, this framework can evaluate complex regional issues like carbon emissions to support policymaking. This research preliminarily validated its application value in identifying opportunities for emission reduction worldwide.