<![CDATA[Tourism is one of the strategic sectors that plays an important role in increasing regional revenue, making effective planning supported by accurate information essential. One of the key pieces of information required is the prediction of visitor numbers as a basis for developing tourism destination management strategies. This study aims to develop a prediction model for the number of visitors to Guci Tourism using the Random Forest algorithm based on historical data. The research employed the Cross Industry Standard Process for Data Mining (CRISP-DM) methodology, which consists of six stages: business understanding, data understanding, data preparation, modeling, evaluation, and deployment. The dataset used in this study consisted of 60 monthly historical records of Guci Tourism from January 2021 to December 2025, obtained from the Department of Youth, Sports, and Tourism of Tegal Regency. The input variables were year and month, while the number of visitors was used as the target variable. The prediction model was developed using the Random Forest Regressor algorithm with an 80:20 split between training and testing data. Model performance was evaluated using Mean Absolute Error (MAE), Root Mean Square Error (RMSE), and the coefficient of determination (R²). The experimental results showed that the model achieved an MAE of 25,950.41, an RMSE of 32,835.06, and an R² value of 0.9624. These results indicate that the Random Forest algorithm is capable of producing visitor predictions that are close to the actual values with good predictive accuracy. Therefore, the Random Forest algorithm can be considered an alternative approach for developing visitor prediction models in the tourism sector.]]>
Copyrights © 2026
