<![CDATA[Yogyakarta is one of the leading tourist destinations in Indonesia, offering various attractions with diverse entrance ticket prices and user ratings. However, unstructured information often makes it difficult for tourists to identify destinations that align with their travel budget and experience preferences. Therefore, this study aims to classify tourist attractions in Yogyakarta based on price and rating using the Random Forest algorithm. The dataset used includes entrance ticket prices, user ratings, visit duration, and geographical distance from the city center of Yogyakarta, allowing a more comprehensive analysis of the relationship between economic value and visitor satisfaction. Prior to model training, data preprocessing and class balancing were performed using the SMOTE technique. The model was evaluated using an 80:20 train-test split and 5-fold cross-validation to obtain more robust and stable performance results. The findings indicate that the features of Price and Rating have the greatest influence on classification outcomes, while geographical distance also plays a meaningful role. The proposed model achieves good classification performance and can serve as a foundation for future development of tourism recommendation systems based on pricing and satisfaction aspects. This research provides a novel contribution to the application of machine learning in the tourism sector, particularly through the integration of geographical factors in tourist attraction price classification.]]>
