Department of Computer Science & IT, The Islamia University of Bahawalpur, Bahawalpur, Pakistan.
Department of Data Science, Faculty of Computing, The Islamia University of Bahawalpur, Bahawalpur, Pakistan.
Sci Rep. 2022 Jul 22;12(1):12508. doi: 10.1038/s41598-022-15880-6.
Educational Data Mining is widely used for predicting student's performance. It's a challenging task because a plethora of features related to demographics, personality traits, socio-economic, and environmental may affect students' performance. Such varying features may depend on the level of study, program offered, nature of subject, and geographical location. This study attempted to predict the final semester's results of students studying Doctor of Veterinary Medicine (DVM) based on their pre-admission academic achievements, demographics, and first semester performance. The imbalanced data led to non-generic prediction models, so it was addressed through synthetic minority oversampling technique. Among five prediction models, the Support Vector Machine led the best with 92% accuracy. The decision tree model identified key features affecting students' performance. The analysis led to the conclusion that marks obtained in Biology, Islamiat, and Urdu at Matric and English at Intermediate level affected the students' performance in their final semester. The findings provide useful information to predict students' performance and guidelines for academic institutes' management regarding improving students' achievement. It is speculated that adoption of digital transformation may help reduce difficulty faced in data collection and analysis.
教育数据挖掘被广泛应用于预测学生的表现。这是一项具有挑战性的任务，因为与人口统计学、个性特征、社会经济和环境相关的大量特征可能会影响学生的表现。这些不同的特征可能取决于学习水平、提供的课程、学科性质和地理位置。本研究试图根据学生的入学前学术成绩、人口统计学特征和第一学期的表现来预测攻读兽医博士(DVM)的学生最后一学期的成绩。不平衡的数据导致了非通用的预测模型，因此通过合成少数过采样技术来解决。在五个预测模型中，支持向量机的准确率最高，为 92%。决策树模型确定了影响学生表现的关键特征。分析得出的结论是，在中学时的生物学、伊斯兰学和乌尔都语以及中级英语的成绩会影响学生在最后一学期的表现。研究结果为预测学生的表现提供了有用的信息，并为学术机构管理部门提供了提高学生成绩的指导方针。有人推测，采用数字化转型可能有助于减少在数据收集和分析方面面临的困难。
