<![CDATA[The continuous growth of esports as a technology-driven competitive activity has increased the demand for professional team management, particularly in assigning suitable roles to athletes based on their individual skills. One of the major challenges faced by coaches is determining athlete roles objectively, as this process is often influenced by subjective judgment and lacks support from systematic data analysis. To address this issue, this study aims to develop a decision support system for determining esports athlete roles in North Sumatra Province by utilizing machine learning approaches. This research applies several classification methods, namely K-Nearest Neighbor (KNN), Naive Bayes, and Support Vector Machine (SVM). The dataset used in this study consists of performance data for esports athletes that have undergone preprocessing stages and are divided into training and testing sets. The evaluation of model performance is conducted using standard classification assessment metrics to compare the effectiveness of each algorithm. The findings show that the KNN and SVM algorithms are better at classifying esports athletes' roles than the Naive Bayes algorithm. These two methods yield more stable and dependable results, rendering them more appropriate for facilitating decision-making processes concerning athlete role assignment. This study is expected to provide practical support for coaches and relevant stakeholders in making objective and data-driven decisions regarding the determination of esports athlete roles. Furthermore, future research can enhance the proposed system by increasing the amount of data and exploring other machine learning techniques to improve overall system performance]]>
Copyrights © 2025
