five

Rajamangala University of Technology Thanyaburi Dropout Dataset (RDD)

收藏
DataCite Commons2023-07-10 更新2025-04-16 收录
下载链接:
https://ieee-dataport.org/documents/rajamangala-university-technology-thanyaburi-dropout-dataset-rdd
下载链接
链接失效反馈
官方服务:
资源简介:
Thailand's national development relies on higher education, posing challenges for the government to enhance graduate competence. High dropout rates impact education quality and student welfare, necessitating a comprehensive study. This research collects a dataset on student dropout and utilizes classification models to predict dropout likelihood at Rajamangala University of Technology Thanyaburi (RMUTT), Thailand. The dataset includes 2,137 undergraduate students from 2013 to 2019 and follows the CRISP-DM model, utilizing internal data sources from ARIT. Leveraging this dataset helps understand the challenges universities face in maintaining student quality and well-being, contributing to effective strategies for improving higher education in Thailand. The dataset analysis identifies influential features in the General Education Course, English for Communication, related to dropout cases. Future research aims to develop a predictive model that utilizes these features to accurately determine dropout likelihood. Upon enrollment, new students' individual features will be input into the model, providing personalized advice on whether to take the course in the current semester or delay it to a later semester, considering its flexible timing. This guidance aims to reduce the dropout rate based on the model's predictions. Overall, this research addresses challenges related to student quality and well-being, enhancing the overall quality of higher education in Thailand.

泰国的国家发展依托高等教育,这给政府提升毕业生综合能力带来了挑战。居高不下的学生辍学率不仅损害教育质量,也对学生福祉造成负面影响,因此亟需开展系统性研究。本研究收集了学生辍学相关数据集,并采用分类模型对泰国兰塔纳功皇家理工大学(Rajamangala University of Technology Thanyaburi, RMUTT)的学生辍学概率进行预测。该数据集涵盖2013至2019年间的2137名本科生,遵循跨行业数据挖掘标准流程(CRISP-DM),采用ARIT内部数据源构建。借助该数据集,有助于深入剖析高校在维持学生培养质量与保障学生福祉方面面临的现实困境,为优化泰国高等教育体系提供切实可行的策略支撑。通过对数据集的分析,本研究识别出通识教育课程、沟通英语两类与辍学案例高度相关的影响特征。未来研究将基于上述特征开发精准的辍学预测模型:学生入学后,可将其个人特征输入该模型,结合课程灵活的授课时间安排,为学生提供个性化建议——是在当前学期修读相关课程,还是推迟至后续学期修读。该指导方案旨在基于模型预测结果降低学生辍学率。总体而言,本研究针对高等教育领域中学生培养质量与学生福祉相关的挑战展开应对,助力提升泰国高等教育的整体质量。
提供机构:
IEEE DataPort
创建时间:
2023-07-10
5,000+
优质数据集
54 个
任务类型
进入经典数据集
二维码
社区交流群

面向社区/商业的数据集话题

二维码
科研交流群

面向高校/科研机构的开源数据集话题

数据驱动未来

携手共赢发展

商业合作