This work is part of an teaching innovation project in Universitat de Barcelona. The aim of the project is to create an automatic tool to process and analyze the accumulated annual curricular data of the students. This tool is based on data science and machine learning techniques to automatically extract patterns and predict behavior of students, dropout and consecutive courses performance, among others. The system will be extremely helpful for the tutor of studies task which can use it in order to take better decisions in their tasks of orientation and enrollment guidance to students.
This repository contains part of the code of the project.
Reference of the paper: S. Rovira, E. Puertas, L. Igual. «Data-driven system to predict academic grades and dropout». PLoS ONE, febrer de 2017. Doi:10.1371/journal.pone.0171207
Abstract: Nowadays, the role of a tutor is more important than ever to prevent students dropout and improve their academic performance. This work proposes a data-driven system to extract relevant information hidden in the student academic data and, thus, help tutors to offer their pupils a more proactive personal guidance. In particular, our system, based on machine learning techniques, makes predictions of dropout intention and courses grades of students, as well as personalized course recommendations. Moreover, we present different visualizations which help in the interpretation of the results. In the experimental validation, we show that the system obtains promising results with data from the degree studies in Law, Computer Science and Mathematics of the Universitat de Barcelona.
Data from law, mathematics and computer science degrees: s1 and s2 csv files of the supporting information
Members of the INDOMAIN Innovation and Teaching Group:
Other members:
Sample of the results in: http://pid-ub.github.io/tfg
Grant 2014PID-UB/068
Grant REDICE-1602