Tags:Artificial Intelligence, Decision Tree, KNN, Naïve-Bayes and Student’s Orientation
Abstract:
Dropping out of school is a complex and multifactorial phenomenon that does not happen overnight. For example, to move from middle school to secondary school, the orientation is currently based only on the students’ choice without taking into account their points. The students are oriented towards branches that do not correspond to their capacities, in addition to the fact that the majority of parents, with a widespread mentality in society, wish to orient their children towards the scientific branch even if their capacities do not allow it, which finally leads to the school abandonment. This paper explores the possibility of making recommendations to students to help them orient themselves well, by analyzing real data collected from many institutions in the Moroccan city of Nador, the data are real and include the period of classes (2018-2019 and 2019-2020 and 2020-2021) of 7720 students of the third college year who have chosen their orientation for the following year, this data was trained on machine learning algorithms. Finally, to make the decision; we compared precision, recall, and f1-score, of three of the classification algorithms: decision tree, naive Bayes, k-nearest-neighbors, our obtained result shows that decision tree is the most suitable for this procedure.
Smart Techniques for Moroccan Students’ Orientation