Predicting student grade repetition at the school level using Machine Learning: a systematic review

The main objective of the research is to determine the state of the art of research on the Prediction of repetition in students at school level using machine Learning. It was carried out through a Systematic Literature Review (SLR) based on Machine Learning for the prediction of students with school repetition between the years 2017-2021. The search strategy identified 47490 papers from digital libraries such as ACM Digital Library, ERIC, Google Scholar, IEEE Xplore, Microsoft Academic, Science Direct and Taylor & Francis Online of which 90 were identified and selected as suitable for the review. The results obtained have focused on studies related to the most efficient Machine Learning algorithms and tools for the prediction of student repetition. As for the conclusions, these present answers about the categories of variables most applied in the prediction of school repetition in students, the metrics used to evaluate the results of the prediction of school repetition, the authors with the highest productivity in the prediction of school repetition, and the most cited articles whose discussions and conclusions are characterized by their objectivity and polarity in the research on the prediction of students with school repetition using Machine Learning