Sign In

Communications of the ACM

ACM Careers

Algorithm Predicts the Academic Performance of Online Students

View as: Print Mobile App Share:
algorithm icon and student at a laptop computer, illustration

The algorithm will help a teacher identify students who are having problems.

A team from the University of Cordoba has designed an algorithm based on fuzzy logic that helps professors predict the performance of online education students and give more personalized assistance where needed to increase success rates.

The FlexNSLVOrd algorithm uses four classifications — Withdrawn, Fail, Pass, Distinction — which allows for better predictions than binary classifications common in previous models, says Amelia Zafra, as associate professor of computer science at the university, and an author of a related article published in Applied Intelligence. Additional authors and developers of the algorithm are Juan Carlos Gámez, Aurora Esteban, and Francisco Javier Rodríguez-Lozano.

The algorithm allows professors to determine which types of characteristics are decisive, and which are not, in terms of gauging performance. It has been tested using a very large set of freely available Open University Public Learning Data (OULAD) from a large sample of students and courses.

From University of Córdoba
View Full Article


No entries found