Peningkatan Akurasi Klasifikasi Ketidaktepatan Waktu Kelulusan Mahasiswa Menggunakan Metode Boosting Neural Network

I Ketut Putu Suniantara (STIKOM Bali)
Gede Suwardika (UPBJJ Denpasar – Universitas Terbuka)
Siti Soraya (Universitas Bumigora)

Jurnal Varian
Vol 3 No 2 (2020)

Supervised learning in Machine learning is used to overcome classification problems with the Artificial Neural Network (ANN) approach. ANN has a few weaknesses in the operation and training process if the amount of data is large, resulting in poor classification accuracy. The results of the classification accuracy of Artificial Neural Networks will be better by using boosting. This study aims to develop a Boosting Feedforward Neural Network (FANN) classification model that can be implemented and used as a form of classification model that results in better accuracy, especially in the classification of the inaccuracy of Terbuka University students. The results showed the level of accuracy produced by the Feedforward Neural Network (FFNN) method had an accuracy rate of 72.93%. The application of boosting on FFN produces the best level of accuracy which is 74.44% at 500 iterations