Enhanced Student Placement Prediction and Skill Recommendation System using Convolutional Neural Network- Bidirectional Long Short-Term Memory with Attention Networks

Predicting student placement results and proposing skills is crucial in education. Current systems frequently show imprecision and inadequately analyse sequential and contextual links among data. This study presents a CNN-Bi-LSTM model using an attention mechanism to resolve these challenges. The suggested system demonstrates superior capabilities in feature extraction, sequential analysis, and feature weighting, surpassing conventional approaches. Significant outcomes consist of 95.4% accuracy, 94.7% F1-score, and an AUC-ROC of 0.96. These measures demonstrate the model's efficacy in forecasting placement results and directing students towards skill improvement. The suggested approach represents a significant enhancement over current methods, providing a comprehensive solution for individualised educational support.