Predicting Students’ Performance Using an Attention-Based Long Short-Term Memory with Conditional Variation Autoencoders and Ensemble Model

The study aims to develop an Attention-Based LSTM (Long Short-Term Memory) model with Conditional Variation Autoencoders (CVAE), and LIME (Local Interpretable Model-Agnostic Explanations), to accurately predict students’ performance. The study employed data Processing and Augmentation using Conditional Variational Autoencoders (CVAE), an Attention-Based Long Short-Term Memory (LSTM) framework, and a final ensemble approach for refined predictions classifying students into three categories. The study utilized a primary dataset consisting of 500 students’ records, the study establishes a performance benchmark. The study revealed that students who frequently raised their hands during lessons were identified by the model as more attentive and participatory, traits that strongly correlated with higher academic performance. It was evident that the developed LSTM with CVAE, and Ensemble model accurately predicts students’ performance. The study concluded the Attention-Based LSTM outperformed the Deep Neural Network, K-Nearest Neighbor, Decision Tree, Support Vector Machine, Naïve Bayes, Random Forest, and Artificial Neural Network which uses the same dataset in predicting student performance. The Attention-Based LSTM consistently outperforms these models, showcasing superior metrics in accuracy, precision, recall, and loss with an accuracy of 89.6%. The study recommended that the Attention-Based LSTM model’s performance highlights how crucial it is for the educational industry to make use of cutting-edge analytical techniques. Also, when developing curricula, policymakers need to take the research on student involvement into account, including components that encourage active participation can result in better academic performance.