Assessment and Evaluation of Different Machine Learning Algorithms for Predicting Student Performance

Table 5

Accuracy results for linear regression (LinR).

Study	Year	Predictive features	Results
[51]	2015	Total playing time, number of videos played, number of rewinds, number of pauses, number of fast forwards, and number of slow play rate use	Accuracy = 76.2%
[44]	2016	Course-specific subdata	RMSE = (0.63, 0.72), Precisition = 26.86%.
[47]	2018	Exercises, homeworks, and quizzes	pMSE = 198.68, pMAPC = 0.81
[48]	2018	Number of views/post of student, course information, student information, submitted assignments, and progress of assignments	Accuracy = 50%
[45]	2018	Summative evaluation attributes	Accuracy = 69%
[37]	2020	Gender, age, parent education, family size, test preparation, father job, mother job, absent days, parent status, travel time, and academic scores	—
[38]	2020	Final grades	—