Precision Assistance for Residents with Subsistence Allowance: Cluster Analysis of Mixed-Type Data Based on K-Prototypes

This paper presents an empirical investigation into the refinement of precision assistance methodologies designed to benefit individuals receiving subsistence allowances. The central objective is to leverage advanced cluster analysis methodologies, particularly the k-prototypes algorithm, to scrutinize heterogeneous datasets, amalgamating both categorical and numerical variables. The overarching goal is to discern distinctive subpopulations within the beneficiary cohort, thereby facilitating the customization of assistance initiatives with greater efficacy. The methodological framework encompasses several key stages, including meticulous data preprocessing, the application of the k-prototypes algorithm for cluster formation, and precision assistance suggestions for clustering results. The findings of this inquiry underscore the efficacy of the proposed approach in delineating population segments accurately, thus offering promising prospects for optimizing resource allocation and refining service provision. In sum, this scholarly endeavor represents a significant stride forward in the realm of precision assistance strategies tailored for marginalized communities, thereby augmenting the operational efficiency and societal impact of extant social welfare endeavors.