Machine Learning-Based Prediction and Analysis of Chinese Youth Marriage Decision

This study investigates the key factors that influence marriage decision among Chinese youth using machine learning techniques. Using data from the China Family Panel Studies (2018-2020), we extracted 1700 samples and filtered 26 significant variables. Seven machine learning algorithms were evaluated, with CatBoost emerging as the most effective. SHAP (SHapley Additive exPlanations) analysis revealed that work-related variables were the most strongly associated with predictions, accounting for 30% of the predictive power, followed by other factors such as demographic and education. Notably, we found that commute time and working hours exceeding 50 min/hours were negatively associated with marriage likelihood, while job satisfactions showed a non-linear relationship with marriage decision. The findings highlight the determinant of work-life balance in marriage decision and the complexity and nonlinear relationship in social decision-making. The objective of this study is to provide scientific data support for policy makers in an era of declining marriage rates in China. This study not only reveals the key factors affecting marriage decision but also provides critical evidence-based support for policymakers to prioritize resource allocation and formulate targeted policies amid declining marriage rates in China.