Two Use Cases of AI for Education: Students Dropout and Low Achievement

Among the many open problems in the learning process, students dropout is one of the most complicated and negative ones, both for students and for institutions. Being able to predict it could help to alleviate its social and economic costs. To address this problem we developed a tool that, by exploiting machine learning techniques, allows us to predict the dropout of first-year undergraduate students. Our experiments were performed by considering real data of students from eleven schools of a major university.
We will also discuss a method for assessing the risk of low achievement in primary and secondary schools. We trained three machine learning models with data collected by the Italian Ministry of Education through the INVALSI large-scale assessment tests. We compared the results of the trained models and evaluated the effectiveness of the solutions in terms of performance and interpretability. We tested our methods on data collected in end-of-primary school mathematics tests to predict the risk of low achievement at the end of compulsory schooling (5 years later). The promising results of our approach suggest that it is possible to generalise the methodology for other school systems and for different teaching subjects.

Relatore

Maurizio Gabbrielli (Università di Bologna)

Docente di riferimento

Marco Bernardo, Giovanni Molica Bisci

Vincoli di partecipazione

Il seminario fa parte del ciclo LAAG.IT - Logica, Algebra, Analisi, Geometria, Informatica Teorica e loro applicazioni, curato dai professori Marco Bernardo e Giovanni Molica Bisci. Il seminario è riservato ai soli studenti del primo anno.

Date

Luogo Data Orario Crediti (CFU)
Aula Olivetti 3 Novembre 2022 11:00-13:00 0,125