Predicting student academic performance using Bi-LSTM: a deep learning framework with SHAP-based interpretability and statistical validation

Abstract

Introduction Educational Data Mining (EDM) involves analysing educational data to identify patterns and trends. By uncovering these insights, educators can better understand student learning, optimise teaching methods, and refine curriculum. One of the main tasks in educational data mining is predicting the student’s academic performance because it makes it possible to provide appropriate interventions supporting students’ achievements. Predicting the student’s academic performance also helps to identify at-risk students and explore the possibility of providing intervention techniques. Methods In this paper, a deep learning model using a Bi-LSTM network is introduced to predict second term GPA. Results The model had an average accuracy of 88.23% and was statistically better than traditional machine learning algorithms such as CatBoost, XGBoost, Hist Gradient Boosting, and LightGBM for accuracy, precision, recall, or F1-score metrics. The results are also analysed with the help of SHAP values for model interpretability to understand feature contributions, making the proposed framework more transparent. The performance of models is also compared using various statistical tests. Discussion The results demonstrate that BI-LSTM performance is significantly different from other models. Hence, the proposed model provides a way to prevent student dropouts and improve academic achievements.