Perbandingan Algoritma Extreme Learning Machine dan Multilayer Perceptron Dalam Prediksi Mahasiswa Drop Out

Abstract

Determined by the university concerned. The high number of drop out students at tertiary institutions can be minimized by policies from tertiary institutions to direct and prevent students from dropping out that detecting at-risk students in the early stages of education is very important to do to keep students from dropping out.
 The purpose of this study is to classify and compare the Extreme Learning Machine and Multilater Perceptron algorithms in predicting student drop out. This study uses two algorithms, namely Extreme Learning Machine and Multilater Perceptron which are feedforward artificial neural network learning methods.
 The data used is 110 data according to the number of students from class 2012 to 2018. The data is taken from the Doctor of Education Management academic information system. In this case how to predict student drop out using the variables Gender, Working Status, Family Status, Age, Semester 3 GPA, Comprehensive Examination, Dissertation Progress, and Publications. The results of the Extreme Learning Machine classification based on a ratio of 80:20 get an accuracy of 95% with a hidden layer of 20 and a Mean Squared Error value of 0.369. Whereas the Multilater Perceptron with the same ratio gets 91% accuracy. From the two models used, it shows that the two artificial neural network algorithms can produce good performance in predicting drop out students.