Penerapan Algoritma Gaussian Naïve Bayes Untuk Klasifikasi Formasi Sepak Bola Berdasarkan Data Atribut Pemain

This study investigates the use of the Gaussian Naïve Bayes algorithm to classify football formations based on a set of player statistical attributes. The main issue addressed arises from the tendency of coaches to determine formations intuitively without relying on systematic and objective data analysis, which may lead to suboptimal tactical decisions. The dataset was obtained from the Kaggle platform and includes numerical attributes such as Pace, Shooting, Passing, Dribbling, Defending, and Physical that collectively describe individual player performance. The analytical workflow follows the Knowledge Discovery in Databases (KDD) framework, consisting of data selection, preprocessing, transformation, and classification model development. Each key attribute was processed into an aggregated value to more comprehensively represent the players’ capabilities. The Gaussian Naïve Bayes model was trained by comparing these aggregated attributes with predefined formation references. The results indicate that the model is capable of grouping formations consistently and generating data-driven recommendations that are more objective than traditional, intuition-based approaches. These findings are expected to contribute to the development of decision-support systems for coaches and analysts, particularly within the broader context of sports analytics.