Multi-Output Based Hybrid Integrated Models for Student Performance Prediction

Abstract

In higher education, student learning relies increasingly on autonomy. With the rise in blended learning, both online and offline, students need to further improve their online learning effectiveness. Therefore, predicting students’ performance and identifying students who are struggling in real time to intervene is an important way to improve learning outcomes. However, currently, machine learning in grade prediction applications typically only employs a single-output prediction method and has lagging issues. To advance the prediction of time and enhance the predictive attributes, as well as address the aforementioned issues, this study proposes a multi-output hybrid ensemble model that utilizes data from the Superstar Learning Communication Platform (SLCP) to predict grades. Experimental results show that using the first six weeks of SLCP data and the Xgboost model to predict mid-term and final grades meant that accuracy reached 78.37%, which was 3–8% higher than the comparison models. Using the Gdbt model to predict homework and experiment grades, the average mean squared error was 16.76, which is better than the comparison models. This study uses a multi-output hybrid ensemble model to predict how grades can help improve student learning quality and teacher teaching effectiveness.