The original dataset supporting the paper "Predicting and Explaining Household Energy Poverty in China Using Bayesian-Optimised XGBoost Models"

The dataset used in this study is mainly derived from the China Family Panel Studies (CFPS), a six-wave balanced panel dataset covering the period from 2012 to 2022. The CFPS is a nationally representative longitudinal survey covering 25 provinces, autonomous regions, and municipalities across China, providing rich household-level information on income, consumption, housing conditions, demographic characteristics, health status, medical insurance, disaggregated energy expenditures, and geographical location, making it particularly suitable for energy poverty research. After removing extreme outliers and imputing missing values using consistent panel data methods, a total of 17,778 valid household observations are obtained, providing a solid empirical foundation for the dynamic identification and predictive modeling of household energy poverty.