Oversampling, Undersampling, Smote SVM dan Random Forest pada Klasifikasi Penerima Bidikmisi Sejawa Timur Tahun 2017

Bidikmisi is tuition assistance from the government for high school graduates (SMA) or equivalent who have good academic potential but economic limitations. Different scholarships that focus on providing awards financial support to those excel. The achievement requirements are aimed at ensuring recipients selected truly and willingness complete higher education. Given of this bidikmisi must really be right person, in study a classification 2017 East Java will carried out, there data not balanced "Accepted" class more than "Not accepted" class. If balanced, almost all algorithms produce much accuracy majority minority Researchers handle imbalances. resampling technique used research related prediction includes techniques, namely Oversampling, Undersampling SMOTE using two methods, SVM Random Forest. Oversampling was chosen because it does reduce amount adds dataset lacking algorithm Synthetic Minority Over-sampling Technique (SMOTE), several produces effective dealing with unbalanced classes reduces overfitting.