Comparison of Collaborative-Filtering Techniques for Small-Scale Student Performance Prediction Task
Comparison of Collaborative-Filtering Techniques for Small-Scale Student Performance Prediction Task
复制标题
DOI：
10.1007/978-3-319-06773-5_16
复制
发表时间：
2015
期刊：
影响因子：
--
通讯作者：
Stefan Pero;Tomáš Horváth
中科院分区：
文献类型：
--
作者：
Stefan Pero;Tomáš Horváth
协作过滤（CF）技术已成功地用于学生成绩预测，但研究主要是在表示（学生、任务、成绩分数）三元组的大而非常稀疏的矩阵上进行的。这项工作调查了CF技术在小型大学或只有少数学生的课程中学生成绩预测的可用性。我们在我们大学收集的一个非常小且不那么稀疏的真实数据集上比较了几种CF技术。实验表明，在这种情况下，这些模型的预测精度不是很好，我们需要利用更多关于学生或任务的信息。
Collaborative-filtering (CF) techniques were successfully used for student performance prediction, however the research was provided mainly on large and very sparse matrix representing (student, task, performance score) triples. This work investigates the usability of CF techniques in student performance prediction for small universities or courses with only a few of students. We compared several CF techniques on a real-world dataset collected at our university which is very small and not so sparse. The experiments show that in such cases the predictive accuracy of these models is not so good and we need to utilize more information about students or tasks.