In the current educational context, the apprentice must be able to benefit from adapted and personalised monitoring by his tutors during his training. These tutors are :
•    the apprentice's company tutor, an employee of the company where the apprentice is doing his work-linked studies. The company tutor's job is to supervise the apprentice and to ensure that the theory that the apprentice has learnt in his training is put into practice.
•    the apprentice's educational tutor, one of the apprentice's teachers. His role is to ensure that the apprentice's training is properly monitored and to make the link between the apprentice's activities in the company and the content of his training.
The apprentice must be able to engage in individual or group projects in order to achieve his professional and study objectives or, if necessary, to find a way of reorienting his objectives with ease. Thus, his tutors must have a permanent view of his activities and his follow-up, which is very complex for them in view of the large amount of data collected by the STUDEA software.

The STUDEA software currently collects a large amount of data (Big Data) through the evaluation questionnaires. The data from these evaluation questionnaires is information related to the apprentice, his/her training and his/her evaluations received during his/her training. This large amount of data represents a wealth of information for an information system, particularly for a recommender system.
At present, the data from the evaluation questionnaires is very little used by STUDEA. Consequently, Effet B wishes to set up a recommendation system that will allow intelligent processing of the data in order to produce a list of strategies that will guide tutors in monitoring their apprentices.
With the development of new artificial intelligence technologies, the recommendation process has entered a new area (Lecun, 2016; Bengio et al., 2021). This evolution has led to hybridization methods between these new artificial intelligence technologies and classical recommender systems (Zhang, et al. 2021). These technologies are associated with sub-domains of artificial intelligence.
The scientific barriers to be overcome in this research are :
a)    Designing pedagogical strategies based on a model of generic skills repositories that can be executed by STUDEA and parameterised by the apprentice's pedagogical tutors.
b)    Designing the meta-models of skills referentials on the basis of the skills model of the training and the study and professional projects of the apprentice.
c)    Automatically assess the apprentice's profile based on a model of skill referentials defined by the automatic system or by the training manager on the basis of the apprentice's objectives. These objectives are defined according to the content of the training and the apprentice's study and professional projects.
d)    To be able to make automatic recommendations on the basis of the results of the assessments obtained from the models and meta-models of competences. These recommendations are intended for those responsible for training and educational tutors.
e)    Make the recommendation understandable to the tutors in order to facilitate the follow-up of his apprentice.
References
Burke, R. (2002). Hybrid recommender systems: Survey and experiments. User modeling and user-adapted interaction, 12(4), 331-370.
Balas, S., & Riem, P. (2014). Conception de référentiels et pédagogie de l’alternance des formations d’ingénieur. Revue internationale de pédagogie de l’enseignement supérieur, 30(30 (3)).
Berrada, R. (2011). Problématique de la gestion des emplois et des compétences et processus d'optimisation par l'intégration des systèmes d'informations.
Barth, B. M. (2011). Le savoir en construction. Retz.
Blons-Pierre, C. (2019). Reconnaissance et validation des acquis de la mobilité géographique et de l’apprentissage à distance: virtualité ou réalité?. Journal of international Mobility, (1), 3-22.
Bydžovská, H. (2016). Course Enrollment Recommender System. International Educational Data Mining Society.
Burke, R. (2000). Knowledge-based recommender systems. Encyclopedia of library and information systems, 69(Supplement 32), 175-186.
Biernacki, C. (1997). Choix de modèles en classification (Thèse de doctorat non publiée). Compiègne.
Caplat, G. (2008). Modèles et métamodèles. PPUR presses polytechniques.
Chen, X., Xie, H., Zou, D., & Hwang, G. J. (2020). Application and theory gaps during the rise of artificial intelligence in education. Computers and Education: Artificial Intelligence, 1, 100002.
Dwivedi, S., & Roshni, V. K. (2017, August). Recommender system for big data in education. In 2017 5th National Conference on E-Learning & E-Learning Technologies (ELELTECH) (pp. 1-4). IEEE
Jadhav, S. D., & Channe, H. (2016). Efficient recommendation system using decision tree classifier and collaborative filtering. Int. Res. J. Eng. Technol , 3 (8), 2113–2118.
Kundu, S. S., Sarkar, D., Jana, P., & Kole, D. K. (2021). Personalization in Education Using Recommendation System: An Overview. Computational Intelligence in Digital Pedagogy, 85-111.
Lecun, Y. (2016). Les enjeux de la recherche en intelligence artificielle. Interstices.
LeCun, Y., Bottou, L., Bengio, Y., & Haffner, P. (1998). Gradient-based learning applied to document recognition. Proceedings of the IEEE , 86 (11), 2278–2324.
Martens, H. H. (1959). Two notes on machine “learning”. Information and Control , 2 (4), 364–379.
Marsland, S. (2014). Machine learning : an algorithmic perspective. Chapman and Hall/CRC.
Mota da Silva, B., & Antunes, C. M. (2021, September). ESTHER: A Recommendation System for Higher Education Programs. In EPIA Conference on Artificial Intelligence (pp. 537-548). Springer, Cham.
Resnick, P., & Varian, H. R. (1997). Recommender systems. Communications of the ACM, 40(3), 56-58.
Zhang, Q., Lu, J., & Jin, Y. (2021). Artificial intelligence in recommender systems. Complex & Intelligent Systems, 7
(1), 439–457.