IRO Journals
Journal of Ubiquitous Computing and Communication Technologies

A Random Forest–Based Framework for Multiclass Student Outcome Prediction and Probabilistic Dropout Risk Stratification

Open Access
Published: 03 November, 2026
Pages: 411-427
  • Shraddha Dattaguru Vedpathak , Shraddha Dattaguru Vedpathak
    P.G. Student, Department of Computer Applications SVERI’s College of Engineering Pandharpur, India
    P.G. Student, Department of Computer Applications SVERI’s College of Engineering Pandharpur, India
  • Anushree Sharad Ashtul Anushree Sharad Ashtul
    Assistant Professor, Department of Computer Applications, SVERI’s College of Engineering Pandharpur, India
    Assistant Professor, Department of Computer Applications, SVERI’s College of Engineering Pandharpur, India
view PDF
view PDF

How to Cite

Vedpathak, Shraddha Dattaguru, and Anushree Sharad Ashtul. 2026. “A Random Forest–Based Framework for Multiclass Student Outcome Prediction and Probabilistic Dropout Risk Stratification”. Journal of Ubiquitous Computing and Communication Technologies 8 (4): 411-27. https://doi.org/10.36548/jucct.2026.4.008.
ACM ACS APA ABNT Chicago Harvard IEEE MLA Turabian Vancouver AMA

Download Citation

Endnote/Zotero/Mendeley (RIS) BibTeX

Keywords

Student Dropout Prediction
Risk Stratification
Intervention Recommendation
Multiclass Outcome Classification
Academic Risk Analytics
Role-Based Monitoring
Student Retention Management

Abstract

Early identification of students at risk of discontinuing their studies requires integrated analysis of academic and student-related characteristics. This research introduces the concept of AI-Based Student Dropout Risk and Intervention System (ADSIRS) that is based on a multi-class classification of the outcome, risk stratification, intervention suggestion, and role-based surveillance in a single architecture. The pre-processed data about students are applied for Machine Learning (ML)-based classification, and the obtained classifications are further mapped to low, medium, and high-risk categories in order to prioritize the intervention process. Testing showed that the accuracy of ADSIRS was 92.0%, and its multiclass ROC-AUC value was 0.94. This system uses a Python-powered web application that incorporates MySQL to link prediction results with role-based dashboards and intervention alerts. This approach creates an effective computing workflow from the processing of student data and outcomes prediction to risk assessment and interventions, which can be used as a method for student retention management.

References

  1. Cannistrà, Marta, Chiara Masci, Francesca Ieva, Tommaso Agasisti, and Anna Maria Paganoni. ”Early-predicting dropout of university students: an application of innovative multilevel machine learning and statistical techniques.” Studies in Higher Education, 2022, vol. 47, no. 9: 1935-1956.
  2. Barramuño, Mauricio, Claudia Meza-Narváez, and Germán Gálvez-García. ”Prediction of student attrition risk using machine learning.” Journal of Applied Research in Higher Education, 2022, vol. 14, no. 3: 974-986.
  3. Katsuragi, Miki, and Kenji Tanaka. ”Dropout prediction by interpretable machine learning model towards preventing student dropout.” In Transdisciplinarity and the Future of Engineering: Proceedings of the 29th International Society of Transdisciplinary Engineering (ISTE) Global Conference, 2022, 678-683.
  4. Song, Zihan, Sang-Ha Sung, Do-Myung Park, and Byung-Kwon Park. ”All-year dropout prediction modeling and analysis for university students.” Applied Sciences, 2023, vol. 13, no. 2: 1143.
  5. Cho, Choong Hee, Yang Woo Yu, and Hyeon Gyu Kim. ”A study on dropout prediction for university students using machine learning.” Applied Sciences, 2023, vol. 13, no. 21: 12004.
  6. Pecuchova, Janka, and Martin Drlik. ”Predicting students at risk of early dropping out from course using ensemble classification methods.” Procedia Computer Science, 2023, vol. 225: 3223-3232.
  7. Krueger, Joao Gabriel Correa, Alceu de Souza Britto Jr, and Jean Paul Barddal. ”An explainable machine learning approach for student dropout prediction.” Expert Systems with Applications, 2023, vol. 233: 120933.
  8. Delen, Dursun, Behrooz Davazdahemami, and Elham Rasouli Dezfouli. ”Predicting and mitigating freshmen student attrition: A local-explainable machine learning framework.” Information Systems Frontiers, 2024, vol. 26, no. 2: 641-662.
  9. Pecuchova, Janka, and Martin Drlik. ”Enhancing the early student dropout prediction model through clustering analysis of students’ digital traces.” IEEE Access, 2024, vol. 12: 159336-159367.
  10. Kuntintara, Wichukorn, Piya Warabuntaweesuk, and Sountaree Rattapasakorn. ”Student dropout prediction using machine learning.” In 9th International Conference on Business and Industrial Research (ICBIR), IEEE, 2024, 0229-0233.
  11. V. Realinho, M. V. Martins, J. Machado, and L. Baptista, “Predict Students’ Dropout and Academic Success,” UCI Machine Learning Repository, 2021. Available: https://archive.ics.uci.edu/dataset/697/predict%2Bstudents%2Bdropout%2Band%2Bacademic%2Bsuccess