Predicting Academic Performance through Data Mining: A Systematic Literature

Abstract

The main objective of this work is to make a systematic review of the literature on the prediction of the academic performance of university students by applying data mining techniques. For this purpose, an exhaustive search was carried out and after the analysis of the documentation collected, aspects such as: methodology, attributes, selection algorithms, techniques, tools, and metrics were considered, which served as the basis for the elaboration of this document. The results of the study showed that the most used methodology is KDD(database knowledge extraction), the most important attribute to achieve prediction is CGPA(academic performance), the most commonly used variable selection algorithm is InfoGain-AttributeEval, among the most efficient techniques are Naïve Bayes, Neural Networks (MLP) and Decision Tree (J48), the most used tools for the development of the models is the Weka software and finally the metrics necessary to determine the effectiveness of the model were Precision and Recall.

How the Predictors of Math Achievement Change over Time: A Longitudinal Machine Learning Approach

“…Self-reported student characteristics, such as demographic variables, are also common data sources used to predict academic performance in the learning analytics community (Hellas et al, 2018). Besides digital traces and demographic characteristics, the majority of learning analytics studies rely on prior performance data (e.g., predicting course performance based on performance in previous courses (Bilal et al, 2022;Daza et al, 2022;Hellas et al, 2018)). Such an approach is intuitive, working on the assumption that past performance predicts future performance, and has indeed produced accurate predictions (e.g., Cetintas et al, 2009).…”

Exploring Online Activities to Predict the Final Grade of Student

“…For this, HEIs managers are looking for ways to reduce dropouts, encourage students to improve their success, and provide a quality education that prepares students well for the labor market so that HEIs be attractive to prospective students. For this reason, student performance is a significant factor for internal and external stakeholder groups in education [3] and a reflection on the quality of the educational services in HEI [4][5][6][7]. Student success prediction is a measure of the quality of the teaching offered [8] and determines success at all levels [9].…”

“…The final goal of all these studies is to improve student performance. Because of this, a large part of this field's research is devoted to the development of student performance prediction models, which allow for predicting student performance [2,3,8,22,31,.…”