Adaptive Prediction Of Online Learning Based On Machine Learning Algorithms

In recent years, with the advancement of society and the rapid development of internet technology, the popularity of online education has been steadily increasing. Presently, nearly every educational institution worldwide, from elementary schools to universities, has incorporated some level of online teaching. While online instruction offers certain conveniences, it will also be accompanied by the emergence of some problems, given the substantial surge in data related to online learning among students, there is an urgent need for robust data processing methods to forecast their suitability for online education. Previous research underscores the effectiveness of machine learning in tackling diverse data classification tasks. However, there is a scarcity of studies comprehensively comparing various machine learning approaches in the context of online education data. This article utilizes seven distinct, parameter-optimized machine learning approaches to explore a range of performance predictions, spanning both binary and multi-class tasks. During the experimental process, four evaluation metrics and visual aids were employed to assess and compare the methods across these tasks, accompanied by a comprehensive discussion of the experimental results. The results of the experiments reveal that the random forest method demonstrates strong versatility across all selected datasets.