Predicting graduation and dropout rates among engineering students using AI techniques
Abstrak
Abstract This study introduces an AI model using a random forest algorithm to predict dropout risk among engineering students at the Instituto Politécnico (IPOLI) of the Federal University of Rio de Janeiro. The model provides academic performance, demographic information, and survey responses. Key factors linked to dropout are identified, providing a practical tool for early intervention and prevention. For instance, proactive mentoring could be initiated as early as week two for students flagged by the model, facilitating timely support. Feature importance analysis highlights strong predictors, such as early GPA and socioeconomic conditions, which are correlated rather than causal. The model allows institutions to identify at-risk students early and supports strategies to enhance retention.
Topik & Kata Kunci
Penulis (2)
Ricardo França Santos
Mathis Berthet
Akses Cepat
- Tahun Terbit
- 2025
- Sumber Database
- DOAJ
- DOI
- 10.1007/s44217-025-01092-3
- Akses
- Open Access ✓