Using Data Science to Predict Student Dropout
Student dropout from universities is a serious issue. Can we use artificial intelligence and data science to predict these dropouts and take preventive measures?
Join the DZone community and get the full member experience.Join For Free
It’s estimated that universities as a whole suffer from a 30% dropout rate, costing a significant amount of money. Being able to reduce this figure is a big issue for the industry.
A team of researchers from the Universidad de Barcelona recently released a study aiming to reduce these levels. They developed a tool that they believe accurately predicts student dropout rates by utilizing machine learning.
“Nowadays, the role of the tutor is more important than ever in order to prevent students from leaving the university and improve their academic performance. The research proposes a system based on objective data to take hidden information which is important for the students’ academic data and therefore to help teachers to offer their students a personal and proactive orientation,” they say.
Firstly, the researchers wanted to test if they could predict whether a student would continue into their second year or not, based purely on their results in the first year. They applied a total of five different algorithms to date from mathematics, computer science, and law degree data. The best of these was able to predict dropout rates with an accuracy of 82%.
The authors wanted to improve upon previous approaches that were based primarily on statistical models that usually used qualitative data gathered from interviews. Whilst this approach has merit, it often fails to take account of the changing circumstances of the student.
“However, machine learning techniques have a predictive use based on objective data, which makes them more adaptable to new data,” the researchers say.
They believe that their machine learning-based approach will offer academics and institutions a warning about students that are at risk — maybe even before they enroll in a course.
It might also prove able to predict the grades those students might earn in future courses, thus allowing teachers to take a preemptive approach to providing advice and support. It’s very much part of an ongoing project of work.
“The following step is to analyze — from an educational perspective — how to use this tool, how to assess its impact and develop a computer application prototype,” they conclude.
Published at DZone with permission of Adi Gaskell, DZone MVB. See the original article here.
Opinions expressed by DZone contributors are their own.