Literature Review for Educational Data Mining Systems—Fahad Bin Sultan University Case Study

The advancement of the learning environment is significantly facilitated by the critical role played by Educational Data Mining through its contributions of state-of-the-art methods, techniques, and applications. The utilization of machine learning (ML) and data mining techniques in exploring and examining educational data has yielded valuable tools for comprehending the student learning environment in recent times. Contemporary academic institutions operate within a context that is marked by intense competition and intricacy. The examination of performance, the provision of superior education, the formulation of tactics for ascertaining the aptitudes of learners, and the identification of future measures are among the predominant difficulties encountered by universities. The focus of the prediction process has been emphasized on analyzing the performance of students using a multitude of parameters. This paper presents a significant contribution in the form of a newly introduced dataset containing student performance data pertaining to the Fairbanks School of Business and Public Administration. This dataset incorporates a range of parameters, including demographic information, academic history, and performance indicators. Utilizing this dataset, we conducted a comprehensive examination of FBSU understudy performance and applied different machine learning and information mining methods, including Support Vector Machine, Choice Woodland, Arbitrary Timberlands, and Calculated Relapse, for classification. Our examination gives bits of knowledge into the variables that altogether influence understudy execution, such as socioeconomics and scholastic foundation. Our findings can inform procedures for assessing student performance and for improving teaching and learning processes in academic institutions.