Predicting student academic performance using multi-model heterogeneous ensemble approach

What is it about?

There have been a lot of inefficiency and low accuracy in predicting student academic performance. Easy model for predicting student academic performance that will help in reducing the attrition rate and increase graduation rate is hereby proposed

Featured Image

Why is it important?

Our findings show that heterogeneous ensemble model prediction are far better than the single classifier models no matter the modelling techniques used. Ensemble techniques improve the accuracy, precision and recall of the model. In addition, there is improved model stability as multiple base models are used to predict the results while the weaknesses and irrelevance among the base models are suppressed by their strengths. The general implications of this research to practice is its ability to accurately help in early identification of students at risk of dropping out of HE from the combination of data sources so that necessary support and intervention can be provided.