A Study on Grade Prediction Based on Course Learning Process Data
Student performance prediction has attracted much attention in the field of smart education,and predicting final exam scores through analyzing course process learning data is crucial for improving teaching quality.Selecting students' learning data from the program de-sign fundamentals(C)course at Qinghai University from 2017 to 2019 as the research object,five machine learning models including support vector machine,random forest,multilayer perceptron,extreme gradient boosting tree,and multiple linear regression were used to evaluate students' final performance in advance based on process learning data.Meanwhile,root mean square error,coefficient of determination,mean absolute error,and mean square error were used to evaluate the predictive performance of the models.The experimental results show that all five machine learning models have good performance in predicting grades,among which the extreme gradient boosting tree has the best perfor-mance.Using machine learning models to deeply analyze students' process learning data and predict their final performance in advance can help teachers optimize the teaching process,enabling students to achieve better learning outcomes and experiences.
国家科技期刊平台
NSTL
万方数据
