Predicting Student Performance to Improve their Employability by Applying Data Mining and Machine Learning Techniques
Year: 2018
Type: article
Abstract: Student performance, dropouts has become an interesting topics in engineering education. To improve student Academic performance, employability and reducing dropouts are the most vital issues in the research. As it has been observed in the literature survey, there are many existing techniques in the Data mining to predict student’s GPAs, grades, dropouts, and desertion. If the student desertion issue is underestimated then one cannot cope the student prediction optimally, which can causes significantly high error. This problem can be minimized with appropriate preventive strategies of Data mining techniques like Matrix Factorization, Rador, and Part in advance. However, the results obtained are still erroneous and to overcome this risk of failure some Machine Learning Approaches like Regression, classification and clustering methods are applied along with DMT which are highly effective. To predict the performance of the students accurately, here we considered various datasets like previous grades, study time, parent’s status, GPA, school support, higher education, internet usage, travel time etc.,. Which crucially carry out the effective performance, grades for the next term. This can help us for the satisfactory graduation and completion of education on time. The comparative study is done on different algorithms such as linear regression, K-means clustering and neural networks using Weka and Azure tools. This can yield us a better student prediction along with preventive strategies for significantly low error. Further, we can extend our study with few more datasets and it might be possible to find a particular student who can perform effectively up to the mark without any failure. This will help us to reduce the drop outs, failure percentage and increases the confidence levels in the students so that, the progression of student performance can be monitor semester by semester
Authors: C. Jayasree, K.K. Baseer
Language: English
Subfield: Computer Science Applications
Field: Computer Science
Domain: Physical Sciences
SDG: Quality education
Open Access status: hybrid
OpenAlex ID: W2887456590