Application Of K-Means For Prioritizing Social Assistance Recipients Based On Dtks Data In Banyuasin Regency

Abstrak

This study aims to improve efficiency and accuracy in the distribution of social assistance in Banyuasin Regency by grouping potential aid recipients based on socio-economic characteristics using the K-Means algorithm. The data used comes from the Integrated Social Welfare Data (DTKS), with cleansing and transformation processes carried out using RapidMiner, and the clustering process continued through an application specifically designed for the implementation of the K-Means algorithm. The study results indicate that this algorithm is capable of forming four clusters of priority aid recipients, namely first, second, third, and fourth priority, thereby reducing mis-targeting compared to the previous manual method. This study is still limited to the use of current-year DTKS data and has not yet included direct field validation. This study contributes to the development of decision support systems in the field of social welfare, particularly in recipient segmentation.