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{198392,
        author = {Daule Suyog Raosaheb and Gaikwad Sakshi Satish and Dethe Komal Vijay and Sonawane Nitesh Vijay},
        title = {Smart Student Risk Prediction using Hybrid Deep Learning},
        journal = {International Journal of Innovative Research in Technology},
        year = {2026},
        volume = {12},
        number = {11},
        pages = {11380-11386},
        issn = {2349-6002},
        url = {https://ijirt.org/article?manuscript=198392},
        abstract = {The exponential growth of digital educational data has enabled advanced analytics in understanding student behavior and academic performance. Traditional methods of student performance assessment rely on statistical averages or manual evaluation, which fail to identify early warning signs of academic risk. This paper presents a comprehensive survey of machine learning and deep learning approaches used for predicting student performance and dropout risks. It also identifies the limitations of existing models and proposes a hybrid deep learning model combining Enhanced Convolutional Neural Network (ECNN) and Residual Network (ResNet) to improve prediction accuracy, model generalization, and early risk detection. The proposed system integrates these models with a web-based MERN stack for real-time analytics and visualization. This study demonstrates that hybrid deep learning architectures significantly outperform conventional classification algorithms, offering more robust and scalable solutions for academic risk prediction.},
        keywords = {Educational Data Mining (EDM), Deep Learning, ECNN, ResNet, Student Risk Prediction, MERN Stack, Machine Learning, Academic Performance, Predictive Analytics.},
        month = {April},
        }