Clustering Performa Pemain Basket Berdasarkan Posisi Dan Statistik Pemain Menggunakan Metode Fuzzy C- Means

Abstract

Satya Wacana Saints Salatiga (SWSS) is one of the professional basketball teams that compete in Indonesian Basketball League (IBL). Player evaluation needs to be carried out to maintain the quality and performance of all players. It can also be used to make some team improvements for the next season. Basketball players’ positions consist of point guard, shooting guard, small forward, power forward, and center. Each position has different strength which can be seen from the statistical points, consisting of PTS (points), AST (assists), BLK (block shoots), REB (rebounds), and STL (steals). The problem is SWSS does not have a system to observe players’ performance based on their positions and statistical points. In this study, the players’ performances is clustered based on their positions and statistical points into three groups, i.e., good, moderate, and poor performance using fuzzy c-means. Since the strength of each position is different, then in this paper, each statistical point is assigned with different weight for different positions. The results of the fuzzy c-means clustering from 15 players of SWSS with weighting are three players with good performance, five players with moderate performance, and seven players with poor performance. Meanwhile, the results of the fuzzy c-means clustering without weighting are five players with good performance, three players with moderate performance, and seven players with poor performance. Both clustering results are compared with the actual performance data, where the accuracy with weighting is 100% and the accuracy without weighting is 86.67%. Clustering with weighting for each statistical point for each player position has an effect on players’ performance. Each player’s position has different strengths in scoring points, assists, block shoots, rebounds, and steals.