Siddalingappa, Rashmi 
ORCID: https://orcid.org/0000-0001-9786-8436, P., Prakash, Gornale, Shivanand S. and Kumar, Satish
(2024)
A Knowledge Based Grade Prediction System using Machine Learning for Higher Education Institutions.
Nanotechnology Perceptions, 20 (S14).
Preview |
Text
A+knowledge+based+Grade+Prediction+system+using+Machine+Learning+for+Higher+Education+Institutions.pdf - Published Version Available under License Creative Commons Attribution. | Preview |
Abstract
The enhancement and preservation of standard in the higher education are pivotal for the enduring viability of Higher Education Institutes (HEIs). National Assessment and Accreditation Council (NAAC) in India introduced a new framework for evaluating HEIs in July 2017 based on qualitative and quantitative data analysis and will be assessed and is carried in two ways Data Validation & Verification (DVV) and the onsite peer team visit. The entire Assessment and Accreditation (A&A) process will take the timeline of six to seven months to complete is time consuming and the human intervention. In this proposed work, a predication model using machine learning techniques is developed to assess the performance of HEIs based on the NAAC Criteria within short timeframe and without human intervention. We have used the Multiclass label classification to predict the Key Indicator Qualitative metric score, and the classification based on the total Quantitative & Qualitative Score. The study utilized four distinct algorithms of Machine learning (ML) for classification: Naive Bayes (NB), Random Forest (RT), K-Nearest Neighbors (K-NN) and Support Vector Machine (SVM). The SVM classification technique exhibited the highest accuracy at 97%, followed by Random Forest at 94%, among the four classifiers.
| Item Type: | Article |
|---|---|
| Status: | Published |
| DOI: | 10.62441/nano-ntp.vi.3001 |
| Subjects: | L Education > L Education (General) Q Science > Q Science (General) > Q325 Machine learning |
| School/Department: | London Campus |
| URI: | https://ray.yorksj.ac.uk/id/eprint/12836 |
University Staff: Request a correction | RaY Editors: Update this record
Altmetric
Altmetric
