One of the goals of the Europe 2020 strategy is that at least 40% of 30-34 years-old complete higher education. Reducing dropout and increasing completion rates in higher education is one of the key strategies for achieving this goal, which is crucial for creating the high-level skills that Europe’s knowledge-intensive economic sectors need. When university dropout occurs, it produces consequences at different levels: society, university and individual students are affected. The complexity of the dropout phenomenon should not be referred only to the different level of impact that produces, but also to the different nature of variables involved. During the academic career, each student develops, experiences and improves capabilities, competencies and attitudes. Would it not be useful to know which factors make the difference between successful and unsuccessful academic careers?

Predictive analytics in higher education is a hot topic among educators and administrators as institutions strive to better support students by becoming more data-informed. Artificial Intelligence, defined as computing systems that are able to engage in human-like processes such as learning, adapting, synthesizing, self-correction and use of data for complex processing tasks1, is one of six technologies with the potential for high impact in higher education2. AI solutions have the potential to structurally change university services and can effectively support the higher learning complex tasks. The development of a predictive algorithm able to identify students who might present features typical of dropout is an innovative approach, which can foster academic performance and produce a great impact on preventing students’ dropout.

STAR.APP project born by the awareness that a more systematic approach should be adopted in the field of academic performance and dropout risk in order to coordinate actions across national borders and in order to acquire a more solid knowledge base on successful actions and good practices. Personal and professional pre-entry counselling, mentoring tutoring systems, and academic support are important to reduce and prevent dropout, but it is time to go further. Understanding the main factors that affect the dropout and creating a system able to provide solutions tailored on specific issues, providing solutions and tools for both students and HEIs to contrast academic disengagement are the expected outcomes of the project.



1S.A.D. Popenici – S. Kerr, Exploring the impact of artificial intelligence on teaching and learning in higher education, in Researche and Practice in Technology Enhanced Learning, Vol. 12, n. 22, 2017, p.2
22020 EDUCAUSE Horizon Report – Teaching and Learning Edition