Application of K-means Clustering Data Mining in Grouping Data of People with Disabilities

Abstract

Data mining is critical in enabling organizations to derive reliable insights from data. Social welfare remains a significant challenge in Indonesia, particularly for people with disabilities, emphasizing the need for targeted strategies. However, developing research has not used natural characteristics according to disability problems. This study utilizes the K-Means Clustering algorithm to analyze and categorize the population of people with disabilities in East Java. The attributes include the type of disability, population size, and regional distribution. We employs a dataset from the East Java Central Bureau of Statistics, comprising 342 data points across eight attributes, including region, disability type, and year. The analysis involves data preprocessing, transformation, clustering, and evaluation using the Davies-Bouldin Index (DBI). The results identify two optimal clusters, achieving the lowest DBI score of 0.097, indicating high cluster quality. Cluster 0 represents regions with fewer people with disabilities, while Cluster 1 highlights areas with higher populations. These findings provide a foundation for developing more focused and inclusive welfare programs tailored to regional needs, enhancing the quality of life for people with disabilities.