THE APPLICATION OF FUZZY LOGIC IN CLUSTERING PROVINCES BASED ON SOCIAL WELFARE, ECONOMIC STATUS, AND HEALTHCARE FACILITIES

Assessing the quality of life across provinces in Indonesia requires a comprehensive evaluation of multiple socio-economic indicators. This study applies Fuzzy Inference Systems (FIS), specifically the Mamdani and Sugeno models, to cluster Indonesian provinces based on five key parameters: Gross Regional Domestic Product (GRDP), crime rate, open unemployment rate, the number of senior high schools, and the number of hospitals. These indicators collectively represent economic status, public safety, employment conditions, educational infrastructure, and healthcare access, fundamental components of social well-being. The use of fuzzy logic allows for nuanced modeling of complex and uncertain data, accommodating both quantitative and qualitative dimensions. Data were obtained from the Indonesian Central Bureau of Statistics and processed using MATLAB’s fuzzy logic toolbox. The results show consistent clustering outputs from both FIS approaches, with most provinces falling within the mid-level cluster. The findings highlight regional disparities that can inform targeted development policies. Moreover, while the ecological dimension was not directly modeled, it is recognized as an underlying factor influencing the observed socio-economic patterns. This framework provides a flexible and adaptable method for future studies incorporating environmental variables to support sustainable regional development.