Mapping Evaluation using Data Mining in the Number of Villages with Sports Fields

Abstract

Sport is an area of achievement in which Indonesia may be quite proud. Many well-known athletes got their start through hobbies. The amount of sports fields in each location can assist children's untapped skills. The study's goal is to map clusters of sports field facilities based on Indonesian regions. The dataset was gathered from the Central Bureau of Statistics (abbreviated as BPS) on the topic of the number of villages in Indonesia having sports grounds availability by province. Football (A1), Volleyball (A2), Badminton (A3), Basketball (A4), Tennis Court (A5), Futsal (A6), and Swimming Pool (A7) are the sports field amenities in concern . As a solution to the challenges outlined, this study employs the K-Means approach. The mapping results are in the form of clusters, which are then evaluated using the Davies-Bouldin index (DBI) depending on field facilities. Each cluster has different mapping results based on sports field facilities, with Football (A1) having the optimal cluster (K=2) with a DBI value of 0.293; Volley ball (A2) having an optimal cluster (K=6) with a DBI value of 0.292; Badminton (A3) having an optimal cluster (K=6) with a DBI value of 0.216; Basketball (A4) having an optimal cluster (K=5) with a DBI value of 0.204; Court Tennis (A5). The overall mapping results show that places such as Maluku, North Maluku, Papua, and West Papua need to upgrade their sports facilities.