Penerapan Data Mining untuk Kelulusan Al-Barqi di Pesantren Salafiyah Syafi’iyah Menggunakan Metode Random Forest

Abstract

Application of data mining methods using Random Forest algorithm to predict student graduation in the Al-Barqi learning program at Pesantren Salafiyah Syafi'iyah. The background of this research is the continued use of manual evaluation systems that have the potential to create subjectivity and lack transparency. The data used comes from student evaluation results, covering aspects of fasohah, tilawah, numerical scores, and discipline. The research process was conducted through stages of data collection, preprocessing, modeling, and implementation using RapidMiner Studio software. The research results show that the Random Forest algorithm is able to provide predictions with a good level of accuracy, as well as identify the score factor as the most dominant variable in determining graduation, followed by aspects of Quranic reading and discipline. These findings confirm that the use of data mining can improve accuracy, objectivity, and transparency in student assessment systems, while supporting digital transformation in pesantren environments. Thus, this research provides data-based recommendations to improve the quality of learning and evaluation systems in pesantren.