Nguyen Thai-Nghe, Andre Busche, and Lars Schmidt-Thieme
[2] have applied machine learning techniques to improve the
prediction results of academic performances for two the real
case studies. Three methods have been used to deal with the
class imbalance problem and all of them show satisfactory
results. They first re balanced the datasets and then used both
cost-insensitive and sensitive learning with SVM for the small
datasets and with Decision Tree for the larger datasets. The
models are initially deployed on the local web.