A K-Medoids Clustering Approach to Controlling Assistance Fund Allocation in Madura
Achmad Jauhari, Ika Oktavia Suzanti, Arifatul Maghfiroh, Amelia Nur Septiyasari, Devie Rosa Anamisa, and Fifin Ayu Mufarroha

University of Trunojoyo Madura

Abstract

Stunting is a condition in which the body does not develop optimally in children as a result of chronic starvation. Stunting is a serious health issue in Madura, with a relatively high frequency. As a result, the local government gives support finances to families experiencing these difficulties. The goal of delivering humanitarian finances is to enhance children^s health and avoid future stunting in youngsters. Aside from that, the stunting assistance financing program in Madura is projected to help overcome the problem of stunting in children while also improving the community^s health and welfare. However, aid finances must be properly classified and administered in order to deliver the greatest benefit to families in need. As a result, the K-Medoids Clustering approach was used to categorize recipients of stunting aid finances in Madura. To address stunting in Bangkalan Regency, data on 14 qualifying criteria for obtaining relief funding was utilized. K-Medoids clustering is used to classify patients based on their stunting status. This simple and convergent method divides data points into clusters, allowing for efficient allocation of funds. This approach helps identify priority groups for interventions to reduce malnutrition rates and helps identify clusters and locations for providing assistance funds. The K-Medoids Clustering approach tries to divide the population into two groups: the cluster not receiving assistance (C1) and the cluster receiving assistance (C2). As a result, 3 sub-districts were declared unfit to receive assistance and 9 sub-districts were recipients of assistance.

Keywords: Stunting, Clustering, K-Medoids, Assistance Fund

Topic: Artificial Intelligence and Data Science