Identifying Non-Performing Students in Higher Educational Institutions Using Data Mining Techniques

Identifying Non-Performing Students in Higher Educational Institutions Using Data Mining Techniques

Deepti Aggarwal, Sonu Mittal, Vikram Bali
Copyright: © 2021 |Pages: 17
DOI: 10.4018/IJISMD.2021010105
OnDemand:
(Individual Articles)
Available
$37.50
Current Special Offers
No Current Special Offers
TOTAL SAVINGS: $37.50

Abstract

The educational institutes are focusing on improving the performance of students by using several data mining techniques. Since there is an increase in the number of drop out students every year, if we are able to predict whether a student will complete the course or not, it is possible to take some preventive actions beforehand. The primary data set used for modelling has been taken from a reputed technical institute of Uttar Pradesh which consists of data of 6,807 students containing 20 academic and non-academic attributes. The most relevant attributes are extracted using CorrelationAttributeEval (in WEKA) technique using Ranker search method which ranks the attributes as per their evaluation. Synthetic minority oversampling technique (SMOTE) filter is applied to deal with the skewed data set. The models are built from eight classifiers that are analysed for predicting the most appropriate model to classify whether a student will complete the course or withdraw his/her admission.
Article Preview
Top

Literature Review

Bhardwaj (2020) used Artificial Neural Network to develop a prediction model for predicting annual medical claims and found that recurrent neural network outperformed feedforward neural network in terms of accuracy.

Complete Article List

Search this Journal:
Reset
Volume 15: 1 Issue (2024)
Volume 14: 1 Issue (2023)
Volume 13: 8 Issues (2022): 7 Released, 1 Forthcoming
Volume 12: 4 Issues (2021)
Volume 11: 4 Issues (2020)
Volume 10: 4 Issues (2019)
Volume 9: 4 Issues (2018)
Volume 8: 4 Issues (2017)
Volume 7: 4 Issues (2016)
Volume 6: 4 Issues (2015)
Volume 5: 4 Issues (2014)
Volume 4: 4 Issues (2013)
Volume 3: 4 Issues (2012)
Volume 2: 4 Issues (2011)
Volume 1: 4 Issues (2010)
View Complete Journal Contents Listing