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{191661,
        author = {Boya Ashok Kumar and Boya Nadavalaiah and Harijana Vinod Kumar and Patlegar Manjunatha and Dr. C V Madhusudan Reddy},
        title = {EduMetric: An Interpretable Web-Based Analytics System for Predicting Student Academic Performance and Dropout Risk},
        journal = {International Journal of Innovative Research in Technology},
        year = {2026},
        volume = {12},
        number = {8},
        pages = {7522-7526},
        issn = {2349-6002},
        url = {https://ijirt.org/article?manuscript=191661},
        abstract = {The rising trend today in institutions of learning is the emphasis to enhance academic performance while at the same time decreasing dropout rates. Despite the constant generation of educational data like internal marks, attendance, semester performance, as well as behavior scores, the traditional monitoring system used in most institutions of learning is manual and inefficient. This type of system tends to be reactionary rather than proactive in nature. EduMetric is presented in this paper, being an extensive web-based analytical system for evaluating, monitoring, and predicting the academic performance and potential for dropping out of education using information related to the institution. Academic performance, attendance rates, and scores for behavior, which are directly set by mentors, are taken into account in the computation of performance, risk, and dropout probability scores using analytical scoring formulas that are heuristic and interpretable for academic institution personnel.
Traditional prediction methods are not applicable here, which make predictions using black box formulas.
It has a modern full-stack technology solution that utilizes the Flask web application framework for back-end computations, the Supabase database (PostgreSQL) for safe and efficient cloud-based data management, while graphics of the interactive results are developed in Plotly.js. Now it has real-time analytics, drill-down displays, and sub-student-level views that facilitate predictive educational counseling. Observations gathered in experiments show that it has the capacity to classify students into appropriate categories concerning results, thus qualified for application in educational settings.},
        keywords = {An Academic performance prediction, educational data analytics, student risk assessment, dropout prediction, learning analytics systems, academic decision support.},
        month = {January},
        }