A Hybrid Deep Learning Model To Predict High-Risk Students In Virtual Learning Environments

Abstract

This project presents “A Hybrid Deep Learning Model to Predict High-Risk Students in Virtual Learning Environments”, an intelligent web-based prediction system developed to identify students who are at risk of low engagement and poor academic performance in online learning platforms. With the rapid growth of virtual education systems, monitoring student participation and learning behavior has become a major challenge for educational institutions. The proposed system uses machine learning and deep learning techniques to analyze student interaction data collected from virtual learning environments and accurately predict student engagement levels. The system considers multiple behavioral and academic features such as weekly study time, quiz score average, forum participation, percentage of video content watched, assignment submission count, login frequency, average session duration, device type, course difficulty, and regional information. The collected dataset is preprocessed using techniques such as missing value removal, label encoding for categorical features, and standard scaling for numerical normalization to improve prediction performance. After preprocessing, the dataset is divided into training and testing datasets for model development and evaluation. Multiple algorithms including XGBoost, Convolutional Neural Network (CNN), Random Forest, and Decision Tree are implemented and compared to determine the most effective prediction model