Machine learning based education data mining through student session streams

Abstract

Recently, significant growth in using online-based learning stream (i.e., elearning systems) have been seen due to pandemic such as COVID-19. Forecasting student performance has become a major task as an institution is focusing on improving the quality of education and students' performance. Data mining (DM) employing machine learning (ML) techniques have been employed in the e-learning platform for analyzing student session streams and predicting academic performance with good effects. A recent, study shows ML-based methodologies exhibit when data is imbalanced. In addressing ensemble learning by combining multiple ML algorithms for choosing the best model according to data. However, the existing ensemblebased model does not incorporate feature importance into the student performance prediction model. Thus, exhibits poor performance, especially for multi-label classification. In addressing this, this paper presents an improved ensemble learning mechanism by modifying the XGBoost algorithm, namely modified XGBoost (MXGB). The MXGB incorporates an effective cross-validation scheme that learns correlation among features more efficiently. The experiment outcome shows the proposed MXGBabased student performance prediction model achieves much better prediction accuracy contrary to the state-of-art ensemble-based student performance prediction model.