Multi-Class Assessment Based on Random Forests

Mehdi Berriri (1) , Sofiane Djema (1) , Gaëtan Rey (1) , Christel Dartigues-Pallez (1)

1 I3S - Laboratoire d'Informatique, Signaux, et Systèmes de Sophia Antipolis

Today, many students are moving towards higher education courses that do not suit them and end up failing. The purpose of this study is to help provide counselors with better knowledge so that they can offer future students courses corresponding to their profile. The second objective is to allow the teaching staff to propose training courses adapted to students by anticipating their possible difficulties. This is possible thanks to a machine learning algorithm called Random Forest, allowing for the classification of the students depending on their results. We had to process data, generate models using our algorithm, and cross the results obtained to have a better final prediction. We tested our method on different use cases, from two classes to five classes. These sets of classes represent the different intervals with an average ranging from 0 to 20. Thus, an accuracy of 75% was achieved with a set of five classes and up to 85% for sets of two and three classes.

Mots clés: machine learning; Random Forest; selection feature; orientation

Domaines: Apprentissage [cs.LG]; Education

Mehdi Berriri, Sofiane Djema, Gaëtan Rey, Christel Dartigues-Pallez. Multi-Class Assessment Based on Random Forests. Education Sciences, 2021, 11 (3), pp.92. ⟨10.3390/educsci11030092⟩. ⟨hal-03625276⟩