Assessment for Learning MOOC’s Updates

Educational data mining to predict students' academic performance: A survey study

A study that uses educational data mining as a source of evidence is Educational data mining to predict students' academic performance: A survey study of Batool et al. (2022). It states that Educational data mining is an emerging field that integrates education and technology to enhance learning outcomes. It leverages data analysis techniques to examine vast amounts of data from schools and colleges. A primary focus is predicting student performance on exams, enabling schools to provide timely support and reduce dropout rates. This paper reviews approximately 260 studies conducted over the past 20 years, investigating the key factors influencing student performance, the various data mining techniques employed, and the commonly used tools. The findings indicate that Artificial Neural Networks (ANN) and Random Forest are the most widely used algorithms, with WEKA being a popular tool for predicting student performance. The study demonstrates that utilizing relevant data, such as student academic records and demographic information, results in more accurate predictions. Furthermore, it emphasizes that eliminating extraneous data enhances outcomes and accelerates the process. The aim of this study is to inform future research on improving prediction accuracy and to assist schools in leveraging data mining to foster student success.

Batool, S., Rashid, J., Nisar, M.W. et al. Educational data mining to predict students' academic performance: A survey study. Educ Inf Technol 28, 905–971 (2023). https://doi.org/10.1007/s10639-022-11152-y