editedbook
Publication: IIP Proceedings Year: 2022, Month: November Page No: 166-173, ISSN/ISBN: 978-93-95632-70-6, DOI/Link: https://rsquarel.org/assets/docupload/rsl2023D291CD06EEF53BF.pdf
MACHINE LEARNING-BASED SELECTION OF PHD ADMISSION
Area/Stream: Artificial Intelligence, Authors: Brajen Kumar Deka, Chinmoy Talukdar Keywords: K-nearest Neighbor; Logistic Regression; Machine Learning; Student Admission Book Name /series: Futuristic Trends in Artificial Intelligence, Volume 2, Book 16, Chapter 16Publication: IIP Proceedings Year: 2022, Month: November Page No: 166-173, ISSN/ISBN: 978-93-95632-70-6, DOI/Link: https://rsquarel.org/assets/docupload/rsl2023D291CD06EEF53BF.pdf
Abstract:
Machine learning is now becoming a crucial decision-support tool in many academic fields. Both educational institutions and students are considered the intended beneficiaries in the field of education. Student admission is a vital problem in educational institutions. The traditional review method can no longer handle a high volume of doctoral applications. This paper discusses the machine learning algorithms for predicting students’ chances of admission to a doctoral program. Students will be able to predict their chances of acceptance of ahead of time. We present a novel dataset called Phd_admission_dataset and examine it to determine the performance of several machine learning methods, such as Logistics Regression and KNN. Experimental results show that the KNN model outperforms the Logistics Regression model.
Cite this: Brajen Kumar Deka, Chinmoy Talukdar,"MACHINE LEARNING-BASED SELECTION OF PHD ADMISSION", Futuristic Trends in Artificial Intelligence, Volume 2, Book 16, Chapter 16, November, 2022, 166-173, 978-93-95632-70-6, https://rsquarel.org/assets/docupload/rsl2023D291CD06EEF53BF.pdf
Views: 4314
Download File
News
