The increasing popularity of Machine Learning in the education business can be attributed to its capacity to enhance several aspects of the educational system. The objective of the present study is to construct a prediction model utilizing Machine Learning techniques in order to forecast students academic performance. In the contemporary competitive landscape, academic institutions are compelled to engage in the proactive task of predicting students academic performance, categorizing them based on their individual talents, and implementing strategies to enhance their success in examinations. In order to identify students who may require early intervention and support, educational institutions must have the capacity to analyze student learning behavior through the application of predictive models for student achievement. The present study utilized a sample of 1087 students enrolled at King Abdulaziz University in Saudi Arabia to make predictions about student scores by employing the GMM model. The results indicated that the mean score achieved by students enrolled in this particular course varied between 14 and 93. The findings also indicate that the optimal model for predicting students academic achievement is the mixture model with four components and varying variances.
A. Alsulaimani, Abdulellah
"Modeling and Classification of Student Performance Based on a Machine Learning Model,"
Information Sciences Letters: Vol. 12
, PP -.
Available at: https://digitalcommons.aaru.edu.jo/isl/vol12/iss12/27