摘要
针对教育数据挖掘中的学习模式预测问题,文章基于随机森林算法开展了学习成绩预测建模研究。首先从480名学生的教育数据中筛选出9个关键特征,其次利用集成随机森林进行预测,并将其与多种常用分类模型进行比较。实验结果表明,所提方法在预测准确性和稳定性方面均优于传统分类模型,为个性化学习决策提供了有效支持。
In response to the problem of predicting learning patterns in educational data mining,this article conducted research on modeling learning performance prediction based on the random forest algorithm.Firstly,9 key features were selected from the educational data of 480 students.Secondly,ensemble random forest was used for prediction and compared with various commonly used classification models.The experimental results show that the proposed method outperforms traditional classification models in terms of prediction accuracy and stability,providing effective support for personalized learning decisions.
作者
宫玉娇
孙玉曼
GONG Yujiao;SUN Yuman(Xiangyang Auto Vocational technical College,Xiangyang,Hubei 441021,China)
基金
湖北省中华职业教育社2024年度课题:职业教育赋能就地城镇化路径研究——基于技能型人才培养的视角(BHZJ2024375)。
关键词
教育数据挖掘
随机森林
分类
educational data mining
random forest
classification
作者简介
宫玉娇(1987-),硕士,讲师,研究方向:教育信息化;孙玉曼(1994-),硕士,讲师,研究方向:职业教育。
