Academic progress monitoring through neural network
To lessen the impact of a low student success rate, it's critical to be able to identify students who are in danger of failing early on, so that more targeted remedial intervention may be implemented. Private colleges use a variety of techniques, including increased tuition, expanded laboratory...
Saved in:
| Main Authors: | , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
REA Press
2021-03-01
|
| Series: | Big Data and Computing Visions |
| Subjects: | |
| Online Access: | https://www.bidacv.com/article_142228_8ac0005d65ffb1bf0553bb605b5aeba9.pdf |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| Summary: | To lessen the impact of a low student success rate, it's critical to be able to identify students who are in danger of failing early on, so that more targeted remedial intervention may be implemented. Private colleges use a variety of techniques, including increased tuition, expanded laboratory access, and the formation of learning communities. The prompt identification of students in danger of failing a given programme is important to both the students and the institutions with which they are registered, as seen by the debate presented below. Students are classified using artificial neural networks and random forests in this article. A private higher education provider provided a dataset of 2000 students. Artificial neural networks were found to provide the best performing model, with an accuracy of 83.24% percent. |
|---|---|
| ISSN: | 2783-4956 2821-014X |