Open AccessClassification of Student Performance Dataset using Machine Learning Algorithms
Author(s) -
K. Maheswari,
P. Deepalakshmi,
K. Ponmozhi
Publication year - 2019
Publication title -
international journal of innovative technology and exploring engineering
Language(s) - English
Resource type - Journals
ISSN - 2278-3075
DOI - 10.35940/ijitee.b1114.1292s219
Subject(s) - machine learning , decision tree , naive bayes classifier , support vector machine , artificial intelligence , computer science , algorithm , k nearest neighbors algorithm , tree (set theory) , scope (computer science) , class (philosophy) , data mining , mathematics , mathematical analysis , programming language
The scope of this research work is to identify the efficient machine learning algorithm for predicting the behavior of a student from the student performance dataset. We applied Support Vector Machines, K-Nearest Neighbor, Decision Tree and Naïve Bayes algorithms to predict the grade of a student and compared their prediction results in terms of various performance metrics. The students who visited many resources for reference, made academic related discussions and interactions in the class room, absent for minimum days, cared by parents care have shown great improvement in the final grade. Among the machine learning techniques we have used, SVM has shown more accuracy in terms of four important attribute. The accuracy rate of SVM after tuning is 0.80. The KNN and decision tree achieves the accuracy of 0.64, 0.65 respectively whereas the Naïve Bayes achieves 0.77.