This paper investigates the role of data-driven poverty alleviation funds (PAFs) in achieving the first Sustainable Development Goal (SDG) – eradicating multidimensional poverty. Using machine learning, spatial statistics, and scenario analysis (Monte Carlo simulation of PAFs-guided Shared Socioeconomic Pathways – PAFs-SSPs), the authors analyze China's poverty alleviation strategy. The study highlights the need for an integrated approach using multidimensional development indicators to address regional disparities and proposes a data-driven model framework applicable to other developing countries. The findings underscore the importance of multidimensional development policies for achieving the first SDG globally.

Di Yang, Weixin Luan, Jun Yang, Bing Xue, Xiaoling Zhang, Hui Wang, Feng Pian