Use of Machine-Learning in Engineering Students’ Trajectories


Students’ trajectories show the student path in the educational system from the beginning to the end of their studies. There are several statistical tools to achieve its understanding and subsequent decision-making by the institution. Each stage of the student’s trajectory can be described by educational, socio-economic, demographic and cultural variables. The purpose of the research is to apply the machine learning techniques of Principal Component Analysis and k-means at the first interpretation of students’ trajectories. It allows to set up clusters and prioritisation variables that organise the academic trajectory characterisation. Techniques were applied to a population of 92 Surveying students of the Engineering School at the University of the Republic (Uruguay), with admissions between 2018 and 2022. For the database processing, the statistical software R was used through RStudio, modelling five variables. In this population, data can be represented by combinations of the original variables after the Principal-Component-Analysis application. The variables that hold the highest level of importance corresponded to: Engineering School admission age and progress level determined with the obtained credits and expected credits ratio. Both variables describe the 57% of the population. On the other hand, k-means clustering has shown three groups of interest generated according to both importance variables obtained with the Principal-Component-Analysis tool. The application of machine learning techniques made it possible to plan and systematise the subsequent qualitative analysis, which included surveys and interviews.

Author Information
Martín Pratto Burgos, University of the Republic, Uruguay
Daniel Alessandrini, University of the Republic, Uruguay
Fernando Fernández, University of the Republic, Uruguay
Ximena Otegui, University of the Republic, Uruguay

Paper Information
Conference: BCE2023
Stream: Educational Research

This paper is part of the BCE2023 Conference Proceedings (View)
Full Paper
View / Download the full paper in a new tab/window

To cite this article:
Burgos M., Alessandrini D., Fernández F., & Otegui X. (2023) Use of Machine-Learning in Engineering Students’ Trajectories ISSN: 2435-9467 – The Barcelona Conference on Education 2023: Official Conference Proceedings
To link to this article:

Comments & Feedback

Place a comment using your LinkedIn profile


Share on activity feed

Powered by WP LinkPress

Share this Research

Posted by James Alexander Gordon