Bayesian Networks for the Early Warning of Student Dropout in Higher Education
Identification
- Clé publique
- radar:r-df46318b7cdc79c40b4994e3c7aff3ad
- Auteurs
- Byron Oviedo
- Année déclarée
- 2026
- Langue déclarée
- en
- Type source
- preprint
- Première détection
- 2026-11-14T01:59:49.873703+00:00
- Dernière observation des métadonnées
- 2026-11-14T01:59:49.873703+00:00
- Dernière vérification HTTP
- Non effectuée
Résumé documentaire — langue originale
The early identification of students at risk of dropping out is central to university tutoring, yet many predictive models are hard for instructors to interpret. This article builds and evaluates a Bayesian network that predicts academic risk in higher education from enrolment information, prioritizing transparency. A quantitative, non-experimental and predictive design was adopted within the field of learning analytics. An open higher-education dataset of 3630 students was used, with eight demographic, socioeconomic and enrolment variables and a binary target distinguishing at-risk students from those who pass. The graph structure was learned through hill-climbing with the Bayesian information criterion, and the conditional probabilities were estimated with a Bayesian estimator; the model was validated on an independent test partition (30%) and through ten-fold cross-validation. The network reached an accuracy of 0.76 and an area under the curve of 0.83, comparable to benchmark classifiers such as naïve Bayes, the decision tree and logistic regression. Payment status, debtor condition, scholarship, age and gender formed the Markov blanket of risk, with estimated probabilities ranging from 10% to 98% depending on the profile. It is concluded that the network provides an interpretable and actionable early-warning system to target tutoring and financial support, with a reproducible and transferable framework for institutional contexts.
Identifiants
- OPENALEX
- https://openalex.org/W7205014182
- DOI
- 10.20944/preprints202609.0077.v1
Repères documentaires
- Famille documentaire
- preprint
- Types déclarés par les sources
- preprint
Les mentions d’entités ne constituent pas une preuve de reconnaissance juridique. La juridiction étudiée est distincte du pays d’affiliation des auteurs.
Sources
OpenAlex · Document 1
Citer cette référence
Byron Oviedo. Bayesian Networks for the Early Warning of Student Dropout in Higher Education. 2026. https://doi.org/10.20944/preprints202609.0077.v1
JSON · CSL-JSON · BibTeX · RIS · CSV · JSON-LD ·
APA, Chicago, ISO 690 : formats bibliographiques fondés sur les champs disponibles. OSCOLA / Bluebook : données structurées uniquement ; aucune conformité juridique complète n’est revendiquée sans vérification des éléments nécessaires.
- APA
- Byron Oviedo. (2026). Bayesian Networks for the Early Warning of Student Dropout in Higher Education. https://doi.org/10.20944/preprints202609.0077.v1
- Chicago
- Byron Oviedo. Bayesian Networks for the Early Warning of Student Dropout in Higher Education. 2026. https://doi.org/10.20944/preprints202609.0077.v1
- ISO 690
- Byron Oviedo. Bayesian Networks for the Early Warning of Student Dropout in Higher Education. 2026. https://doi.org/10.20944/preprints202609.0077.v1
Warning: Undefined array key "last_link_verified" in /home/clients/e27d81e12f04d2bfd747aa264540ac56/sites/_UDTR_APP/legal_library_reference.php on line 31
UDTR — Bibliothèque juridique mondiale des droits de la Nature. Bayesian Networks for the Early Warning of Student Dropout in Higher Education. Notice documentaire: https://www.declarationuniverselledesdroitsdelarbre.org/global-rights-of-nature-radar/reference/r-df46318b7cdc79c40b4994e3c7aff3ad/ · Dernière vérification HTTP : non effectuée
Données de cette version figée
Dossiers et relations documentaires
Rôles des sources
Source bibliographique / publication d’origine · https://doi.org/10.20944/preprints202609.0077.v1
Un lien vers une autorité ne prouve pas à lui seul une affirmation juridique. Les résumés et les textes intégraux restent soumis aux conditions de leur source.
Statut documentaire
Pertinence à examiner
Bibliothèque
Cette identité n’est pas encore intégrée à la Bibliothèque juridique.