The application of data mining in the evaluation of Hadrah tests at Pesantren Salafiyah Syafi'iyah is explored using the Random Forest algorithm. Hadrah, a form of Islamic artistic performance involving vocal and percussion elements, is integral to the cultural and spiritual life in Islamic boarding schools. The objective of this research is to enhance the accuracy and objectivity of performance assessments in Hadrah, particularly in the context of competition or educational evaluation at Pesantren Salafiyah Syafi'iyah. By utilizing the Random Forest method, which is a robust machine learning technique, the study aims to minimize the subjectivity and inconsistency inherent in traditional evaluation methods. The study leverages secondary data from previous Hadrah tests, applying preprocessing steps to ensure the data is suitable for analysis. The results show that Random Forest provides a high level of precision in classifying participants based on key assessment features such as tempo, consistency, and overall performance. This method contributes significantly to improving the reliability and fairness of the evaluation process, ensuring a more standardized approach to assessing artistic skills in the context of Islamic traditions. The findings suggest that data-driven approaches can play a pivotal role in preserving and promoting Islamic arts while enhancing the educational process.