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{196287,
        author = {PRAVIN DABHADE and Mahesh Jagtap and Rutika Chavan},
        title = {A Transparent Deep Learning Framework for Student Performance Prediction with SHAP and LIME},
        journal = {International Journal of Innovative Research in Technology},
        year = {2026},
        volume = {12},
        number = {11},
        pages = {3625-3631},
        issn = {2349-6002},
        url = {https://ijirt.org/article?manuscript=196287},
        abstract = {Predicting student academic outcomes at an early stage gives institutions the opportunity to intervene before a learner falls too far behind. Although deep learning architectures have repeatedly demonstrated strong predictive power on student data, their opaque decision-making process continues to hinder practical acceptance among educators and policymakers who require clear, auditable reasoning. This study develops a transparent prediction pipeline that couples a hybrid Long Short-Term Memory and Feedforward Neural Network (LSTM-FNN) model with two complementary post-hoc explanation techniques: SHapley Additive exPlanations (SHAP) and Local Interpretable Model-agnostic Explanations (LIME). Experiments conducted on the publicly available UCI Student Performance Dataset show that the proposed model attains 94.3 % accuracy and an AUC-ROC of 0.951, surpassing four conventional baselines. SHAP attribution scores indicate that prior-term grades and absenteeism are the dominant predictors, while LIME provides student-specific reasoning that educators can act upon immediately. The framework is designed to be dataset-agnostic and is readily extensible to other higher-education contexts, including MCA and engineering programmers in India.},
        keywords = {Explainable Artificial Intelligence (XAI); Student Performance Prediction; SHAP; LIME; LSTM; Educational Data Mining; Interpretable Machine Learning; Deep Learning},
        month = {April},
        }