Copyright © 2026 Authors retain the copyright of this article. This article is an open access article distributed under the Creative Commons Attribution License which permits unrestricted use, distribution, and reproduction in any medium, provided the original work is properly cited.

@article{190556,
        author = {G. SIVARAJAN and V. MAGESWARI},
        title = {A machine learning approach for predicting academic performance and risk levels},
        journal = {International Journal of Innovative Research in Technology},
        year = {2026},
        volume = {12},
        number = {8},
        pages = {3375-3379},
        issn = {2349-6002},
        url = {https://ijirt.org/article?manuscript=190556},
        abstract = {Identifying students at risk of underperformance is important for their greater outcomes and failure rates within institutions of learning. There have been recent breaks throughs in incorporating Artificial Intelligence and Machine Learning in identifying predictive models for informed decision making in academics. Artificial Intelligence-based Student Performance Prediction System for predicting and identifying students at High Risk, Medium Risk, and Low Risk categories. In this system, a Random Forest Regressor is used to analyze several important parameters related to academics and behavior, like parameters related to studying time, attendance ratio, previous test results, failure ratio, availability of internet connectivity, and health conditions. In this system, a web interface can be achieved by employing a combination of Flask and SQLite technology. The proposed system comprises two distinct interfaces: Teacher Dashboard and Student Portal.
Experiments carried out in artificially generated datasets for students are able to prove the effectiveness of the system in providing accurate predictive results, along with the ability to develop learning plans for students by utilizing AI, which are designed to address the individual needs of students. The proposed system creates a scalable intervention for learning that helps both teachers and students in improving their learning performances.},
        keywords = {Student Performance Prediction, Predictive Analytics in Education, Machine Learning, Random Forest Regressor, Flask Web Application, Academic Risk Assessment, Educational Data Mining, AI-Based Learning Support System.},
        month = {January},
        }