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{196056,
        author = {VUNA VENKATA VIDYASAGAR and A. Gopi Chandrika and J. Sampath Eswar Sai Kumar and G. Seshagiri and A. Shyam},
        title = {Intelligent System for Student Performance Prediction Using AI},
        journal = {International Journal of Innovative Research in Technology},
        year = {2026},
        volume = {12},
        number = {11},
        pages = {1753-1757},
        issn = {2349-6002},
        url = {https://ijirt.org/article?manuscript=196056},
        abstract = {Student performance prediction is an important area in education, as it helps in identifying students who may need additional support and enables timely academic intervention. In this study, an intelligent system is developed to predict student performance in mathematics using machine learning along with explainable artificial intelligence techniques.
The system is built using a dataset that includes both demographic and academic factors such as gender, race/ethnicity, parental education level, type of lunch, participation in test preparation courses, and scores in reading and writing. A Linear Regression model is used to understand how these factors influence the mathematics score. To improve the model’s effectiveness, preprocessing methods like one-hot encoding and feature scaling are applied.
The developed model is deployed through a FastAPI backend and connected to an interactive web interface, allowing users to input data and obtain predictions instantly. To ensure the model is transparent and understandable, SHAP (SHapley Additive exPlanations) is used to interpret the contribution of each feature to the prediction.
The results show that the model performs well when important academic features are included, while its performance decreases significantly when these features are removed. This emphasizes the importance of selecting relevant features in predictive modelling.
Overall, the proposed system not only provides accurate predictions but also offers meaningful insights, making it useful for educators and institutions in monitoring student performance and making informed decisions.},
        keywords = {Student Performance Prediction, Machine Learning, Linear Regression, Explainable AI, SHAP, Educational Data Mining.},
        month = {April},
        }