Parametric Study of Student Learning in IT Using Data Mining to Improve Academic Performance

Abstract

Data mining in education is a developing interdisciplinary research field also known as educational data mining (EDM). The goal is to understand students' learning process and identify the way by which they can learn to improve educational outcomes. Learning using IT is one of the most widely used methods for education in modern days. Digital learning gives students an experience of individual learning at any time as well as anywhere, so students get more interest, flexibility at learning. Knowing the preferences of students learning will help the instructors to design better learning materials and teaching styles. We have surveyed on the students of undergraduate level and evaluated the students in three categories: good, average and excellent. We have used four classification models: Support Vector Machine (SVM), Logistic Regression (LR), Decision Tree and Random Forest (RF) model to predict the performance of students on basis of the impact of IT and other study mediums based on their results. In this article, we have identified different parameters or features from five different learning sectors or fields which can give an impact on the student's learning process. So, we have processed in a way that will find out the data mining model which can give better accuracy of student's performance and also can find out which parameters or features among the five fields are playing a great role in their academic results. Moreover, we can apply these features by inspiring good or average students to improve their learning process.