Implementasi Algoritma Neural Network dalam Memprediksi Tingkat Kelulusan Mahasiswa

Abstract

Higher education institutions are demanded to be quality education providers. One of the instruments used by the government to measure the quality of education providers is the number of graduates. The higher the graduation level, the better the quality of education and this good quality will positively influence the value of accreditation given by BAN-PT. Therefore, in this study the researchers provided input for research conducted at Bhayangkara Jakarta Raya University to predict student graduation rates using the Neural Network algorithm. Neural Network is one method in machine learning developed from Multi Layer Perceptron (MLP) which is designed to process two-dimensional data. Neural Network is included in the Deep Neural Network type because of its deep network level and is widely implemented in image data. Neural Network has two methods; namely classification using feedforward and learning stages using backpropagation. The way Neural Network works is similar to MLP, but in Neural Network each neuron is presented in two dimensions, unlike MLP where each neuron is only one dimensional in size. The prediction accuracy obtained is 98.27%.