How to choose the most appropriate courses to study throughout the learning process remains a question interested in by many students. Students often choose suitable courses according to their interests, needs, and advice from supporting staff, etc. This paper presents the results in developing a course recommendation system that will select appropriate courses for each student studying a major in the following semesters based on his/her current academic performance. We have applied several techniques based on data mining and learning analytics to predict students’ learning outcomes in the next semester and developed a model to select the appropriate courses based on such a recommendation system. Besides, our study has focused on comparing the effectiveness of predictive learning methods based on collaborative filtering. Experiments analyzed the learning results of 510 students who enrolled in the courses from 2015 to 2019 and showed that the Matrix Factorization method is the most effective. Also, the paper has proposed procedures and constraints applicable to different training curricula.

如何选择最合适的课程来学习整个学习过程仍然是许多学生感兴趣的问题。学生经常根据自己的兴趣，需求和支持人员的建议等选择合适的课程。本文介绍了开发课程推荐系统的结果，该系统将根据以下课程为每个学期的主修学生选择合适的课程。她目前的学业表现。我们应用了基于数据挖掘和学习分析的多种技术来预测下学期的学生学习成果，并开发了一种基于这种推荐系统选择合适课程的模型。此外，我们的研究集中在比较基于协作过滤的预测学习方法的有效性。实验分析了2015年至2019年招收的510名学生的学习结果，结果表明，矩阵分解法是最有效的方法。此外，本文还提出了适用于不同培训课程的程序和约束条件。