Educational Data Mining as a Predictive Strategy to Improve Performance and Reduce Dropout in Distance Education – UNED Costa Rica
Αποθηκεύτηκε σε:
| Συγγραφέας: | |
|---|---|
| Μορφή: | artículo original |
| Κατάσταση: | Versión publicada |
| Ημερομηνία έκδοσης: | 2026 |
| Περιγραφή: | This research at UNED analyzes the potential of Educational Data Mining (EDM) to predict performance and reduce dropout rates in distance education. By applying predictive techniques to the Introduction to Computing course, significantly increased passing rates and reduction in failures was achieved. Tools such as ORANGE were evaluated for their ease of use and potential for personalized interventions. The results confirm that EDM strengthens evidence-based pedagogical decision-making, supports formative accompaniment, and fosters continuous improvement. The study also emphasizes the importance of training faculty in data analysis and recommends extending EDM implementation in other courses to consolidate a student-centered educational culture. |
| Χώρα: | Portal de Revistas UNED |
| Ίδρυμα: | Universidad Estatal a Distancia |
| Repositorio: | Portal de Revistas UNED |
| OAI Identifier: | oai:revistas.uned.ac.cr:article/6582 |
| Διαθέσιμο Online: | https://revistas.uned.ac.cr/index.php/index/article/view/6582 |
| Λέξη-Κλειδί : | data mining distance education higher education predictive analysis educational technology minería de datos educación a distancia enseñanza superior análisis predictivo tecnología educativa |