<![CDATA[Motorcycle key damage is often a problem for users, while the identification process still relies on technicians, which can be time-consuming and subjective. This study develops a classification system for motorcycle key damage levels using the Random Forest method with hyperparameter optimization. The dataset consists of 1,000 samples collected through observation and technician interviews, with data preprocessing using the SMOTE technique to address class imbalance. The model is trained and optimized with Random Forest using GridSearchCV and evaluated based on accuracy, precision, recall, and F1-score. The results show that the optimized Random Forest model achieves an accuracy of 85.5%, an improvement from 82% before tuning, enabling faster and more accurate identification of motorcycle key damage levels. The implementation of this system is expected to improve repair service efficiency and help users take action before the damage worsens.]]>
Copyrights © 2025
