The Implementation Of The Extreme Learning Machine Method For Predicting New Student Enrollment At SMK Negeri 1 Of South Bengkulu

Abstract

SMK Negeri 1 of South Bengkulu is one of the vocational high schools located in Bengkulu Selatan Regency. At the beginning of each academic year, the school opens admissions for new students. The number of new student registrations has fluctuated from year to year, which may affect the school's resource planning and management. The implementation of the Extreme Learning Machine (ELM) method for predicting the number of new student enrollments at SMK Negeri 1 of South Bengkulu is capable of providing predictive information regarding the number of applicants for the upcoming academic year. The prediction results can be utilized as a decision-support tool for school administrators in planning New Student Admission (PPDB) activities, particularly in managing educational resources, facilities and infrastructure, as well as budget planning. The student enrollment prediction system developed in this study is web-based and utilizes PHP as the programming language and MySQL as the database management system. Based on historical data on new student enrollments at SMK Negeri 1 of South Bengkulu over the past ten academic years, from the 2015/2016 academic year to the 2024/2025 academic year, the system was able to generate a prediction of 342 new student enrollments for the 2025/2026 academic year using the Extreme Learning Machine method. The resulting error rate was 7.54%, which falls within the category of very high prediction accuracy.