基于多算法融合的在线学习成绩精准预测研究

Research on Precise Prediction of Online Learning Performance Based on Multi-algorithm Fusion Strategy

学习成绩早期预测是解决在线学习辍学率高、参与度低等问题的关键要素,如何实现在线学习成绩精准预测是亟待解决的科学议题。已有研究主要采用单一算法训练单一分类器和集成分类器预测学习成绩,然而该方法预测精准性较低。研究设计基于多算法的在线学习成绩预测框架,融合神经网络、决策树、K-近邻、随机森林和逻辑回归算法预测学习者在线学习成绩,并进行了预测性能分析。研究结果表明,多算法融合预测精准性优于单一算法,预测结果在应用中有助于学习者意识到潜在的学业风险,促进其积极参与学习活动,显著提高在线课程学习质量。

Early prediction of academic performance is a key element to solve the problems of high dropout rate and low participation in online learning.How to achieve accurate prediction of online learning performance is a scientific issue that needs to be resolved urgently.Existing studies mainly use a single algorithm to train single classifier and integrated classifier to predict learning performance.However,this method has low predictive performance.The study designs an online learning performance prediction framework based on a multi-algorithm fusion strategy,which integrates Neural Networks,Decision Trees,K-Nearest Neighbors,Random Forests,and Logistic Regression algorithms to predict learners’online learning performance.The research result shows that the accuracy of multi-algorithm fusion prediction is better than that of a single algorithm.The prediction result can help students realize potential academic risks,actively participate in learning activities,and significantly improve the quality of online course learning.