Using Bayesian Networks and Machine Learning to Predict Computer Science Success

Bayesian Networks and Machine Learning techniques were evaluated and compared for predicting academic performance of Computer Science students at the University of Cape Town. Bayesian Networks performed similarly to other classification models. The causal links inherent in Bayesian Networks allow for understanding of the contributing factors for academic success in this field. The most effective indicators of success in first-year `core' courses in Computer Science included the student's scores for Mathematics and Physics as well as their aptitude for learning and their work ethos. It was found that unsuccessful students could be identified with approximate to 91% accuracy. This could help to increase throughput as well as student wellbeing at university.