Predicting university major selection and academic performance through the combination of Apriori algorithm and deep neural network

• Published in: Education and information technologies Vol. 30; no. 1; pp. 333 - 346
• Main Authors: Ouassif, Kheira, Ziani, Benameur
• Format: Journal Article
• Language: English
• Published: New York Springer US 01.01.2025; Springer Nature B.V
• Subjects: Academic achievement; Accuracy; Algorithms; Cognitive Ability; College Science; Computer Appl. in Social and Behavioral Sciences; Computer Science; Computers and Education; Data Collection; Data mining; Education; Educational Change; Educational Technology; Employment Level; Enrichment Activities; Family Income; Higher education; Influence of Technology; Information Systems Applications (incl.Internet); Information Technology; Intelligence; Learning Management Systems; Learning Processes; Literature Reviews; Majors (Students); Networks; Neural networks; Parent Participation; Search Strategies; Student Participation; Student Surveys; Success; University students; User Interfaces and Human Computer Interaction; University major selection; Educational data mining; Deep neural network; Student’s performance; Association rule
• ISSN: 1360-2357; 1573-7608
• DOI: 10.1007/s10639-024-13022-1

The integration of educational data mining and deep neural networks, along with the adoption of the Apriori algorithm for generating association rules, focuses to resolve the problem of misdirection of students in the university, leading to their failure and dropout. This is reached through the development of an intelligent model that predicts the right path for each student based on their academic background, preferences and skills. While we observed no impact of the Socio-Economic and Family Background features on the students’ performance. And this is what was included in this research paper.