This paper is published in Volume-5, Issue-5, 2019
Area
Machine Learning
Author
Shahina K. M.
Org/Univ
University of Calicut, Malappuram, Kerala, India
Pub. Date
17 October, 2019
Paper ID
V5I5-1277
Publisher
Keywords
Data Analytics, Linear Regression, Random Forest, Gradient Boosting, Logistic Regression

Citationsacebook

IEEE
Shahina K. M.. An automated prediction system for academic performance, International Journal of Advance Research, Ideas and Innovations in Technology, www.IJARIIT.com.

APA
Shahina K. M. (2019). An automated prediction system for academic performance. International Journal of Advance Research, Ideas and Innovations in Technology, 5(5) www.IJARIIT.com.

MLA
Shahina K. M.. "An automated prediction system for academic performance." International Journal of Advance Research, Ideas and Innovations in Technology 5.5 (2019). www.IJARIIT.com.

Abstract

Data analytics has a key role in the educational system and it helps to predict the student’s performance based on academic and non-academic details. Any institution spends huge amount of work to analyze student performance. Accuracy of manual prediction depends on different factors like the relation between the student and teacher, the time spends for the analysis, etc. So prediction with high accuracy requires huge amount of time and mental work. This paper presents a system for student performance analysis and grade prediction. This system greatly helps both the academicians and students. Grade prediction system helps the students to improve their performance and reduce dropout. And academicians can draw a clear picture of each student in the institution by this prediction. This scenario uses a data set consist of 33 features of 382 students. Python Anaconda distribution is the tool used for analysis and prediction. Four classification methods, linear regression, random forest, gradient boosting and logistic regression were used. The result shows that random forest outperforms all other methods inaccuracy. The system also finds the high influential factors and calculates the correlation between the final mark with different features like study time, father occupation and time spent for internet access etc.
Paper PDF