Otimização e automação da predição precoce do desempenho de alunos que utilizam juízes online: uma abordagem com algoritmo genético

Resumo

In this work, we present an approach to predict student performance in the very first two weeks from CS1 classes which use programming online judges. We performed the prediction with a binary classification, i.e., we estimated whether the student succeeded or failed. To do so, we employed a method using an evolutionary algorithm to build and optimize automatically the machine learning pipeline. We trained the predictive model with data from 9 different courses run during 6 terms (2016-2018). As a result, we achieved an AUC of 0.87 on the validation set.