Decoding Green Consumption Behavior Among Chinese Consumers: Insights from Machine Learning Models on Emotional and Social Influences

This study examined the diverse factors influencing green consumption behavior among Chinese consumers through a comprehensive, data-driven approach that integrated multiple machine learning models, including Gaussian naïve Bayes, K-nearest neighbor, multilayer perceptron, and XGBoost models. By analyzing emotional, product-related, cultural, social, and personal dimensions, this research identified key determinants that shape consumer engagement in sustainable consumption. Unlike conventional studies that rely on linear models or survey-based analyses, this study leveraged machine learning to uncover complex, nonlinear interactions between these factors. The findings reveal that emotional drivers, particularly guilt and pride, play a pivotal role in green consumption decisions, while cultural and product-related factors also exhibit significant influence. This study contributes methodologically by employing a multidimensional, multilevel analytical framework, enhancing the robustness of the findings. Furthermore, the results underscore the importance of policy and marketing strategies that effectively target emotional and social influences to cultivate a sustainable consumer culture. These insights provide actionable recommendations for policymakers and businesses seeking to promote green consumption and advance global sustainability efforts.