<![CDATA[The selection of study programs and the selection process for new student admissions are crucial stages that have an impact on the smooth running of studies and students' future careers. However, this process is often still done subjectively, thus potentially causing a mismatch between interests, abilities, and the chosen study program. This research aims to implement the Random Forest algorithm, analyze the factors that influence acceptance, and determine the performance of the prediction model generated by the Random Forest algorithm in assisting new student admissions for the National Selection Based on Test (SNBT) pathway at Universitas Singaperbangsa Karawang. This research uses the Knowledge Discovery in Database (KDD) method which consists of 5 stages, namely Data Selection, Preprocessing, Transformation, Data Mining, and Evaluation. The data used was 815 new student data of Universitas Singaperbangsa Karawang, which included UTBK scores, school background, and choice of prospective student study programs. In the Transformation and Data Mining stages, 4 data splitting scenarios were carried out, namely 90:10, 80:20, 70:30, and 60:40. The best performance with the Random Forest model is generated by the 80:20 data splitting scenario with an accuracy value of 0.945, precision of 0.937, recall of 0.943, f1-score of 0.940 and AUC value of 0.983.]]>
Copyrights © 2025
