Applying and comparing machine learning classification algorithms for predicting the results of students. (17th February 2020)

• Record Type: Journal Article
• Authors: Rajak, Akash; Shrivastava, Ajay Kumar; Vidushi,
• Is Part Of: Journal of discrete mathematical sciences & cryptography. Volume 23:Number 2(2020)
• Page Start: 419
• Page End: 427
• Publication Date: 2020-02-17
• Subjects: 68U99; Linear regression -- Artificial intelligence -- Student assessment; Computer science -- Mathematics -- Periodicals; Cryptography -- Periodicals; Computer science -- Mathematics; Cryptography; Periodicals; 004.0151
• DOI: 10.1080/09720529.2020.1728895
• Languages: English
• ISSNs: 0972-0529

Abstract

Abstract: The machine learning algorithms can be applied to educational domains for the prediction of results, analysis of weak students, to analyse other features in data apart from grades, technical education for calculating the attainments in outcome-based education etc. In this research the different classification machine learning algorithms are applied on datasets having features like student marks, family education, fathers' job, attendance in school etc and model's performance is calculated. Further, some features have been removed from the dataset in which the target value completely depends on student marks and further the models are evaluated. The results were very interesting, and it reveals that without knowing previous marks of students we can predict the future marks. The study would certainly helpful in educational institutions where we can find future grades which would help in finding the weak students. The execution time of different algorithms is also recorder on Graphics and Tensor processing units.