A Machine Learning Approach to Detect Student Dropout at University
Journal: International Journal of Advanced Trends in Computer Science and Engineering (IJATCSE) (Vol.10, No. 6)Publication Date: 2021-12-07
Authors : Shiful Islam Shohag Masum Bakaul;
Page : 3101-3107
Keywords : ;
Abstract
In universities, student dropout is a major concern that reflects the university's quality. Some characteristics cause students to drop out of university. A high dropout rate of students affects the university's reputation and the student's careers in the future. Therefore, there's a requirement for student dropout analysis to enhance academic plan and management to scale back student's drop out from the university also on enhancing the standard of the upper education system. The machine learning technique provides powerful methods for the analysis and therefore the prediction of the dropout. This study uses a dataset from a university representative to develop a model for predicting student dropout. In this work, machine- learning models were used to detect dropout rates. Machine learning is being more widely used in the field of knowledge mining diagnostics. Following an examination of certain studies, we observed that dropout detection may be done using several methods. We've even used five dropout detection models. These models are Decision tree, Naïve bayes, Random Forest Classifier, SVM and KNN. We used machine-learning technology to analyze the data, and we discovered that the Random Forest classifier is highly promising for predicting dropout rates, with a training accuracy of 94% and a testing accuracy of 86%.
Other Latest Articles
- The Crossbreed Invariant Optimization MSVM Method for Effective Diagnosis of Pneumonia from Chest X-Ray Images
- University Computer Network Vulnerability Management using Nmap and Nexpose
- User Engagement and User Design on Online Shopping Apps
- Ways of overcoming professional deformation employee MIA system
- Identity and Chaplaincy in Ukraine
Last modified: 2021-12-16 23:27:25