Enhanced Butterfly Optimization and Deep Learning Algorithm for Student Placement Prediction
Campus Placement (CP) is regarded in India as a crucial factor in determining universities or college's ranking and recognition. A university's standing and reputation are greatly influenced by the number of students it places in jobs and the average compensation offered to those students...
Saved in:
| Main Authors: | , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
International Transactions on Electrical Engineering and Computer Science
2025-07-01
|
| Series: | International Transactions on Electrical Engineering and Computer Science |
| Subjects: | |
| Online Access: | https://iteecs.com/index.php/iteecs/article/view/139 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| Summary: | Campus Placement (CP) is regarded in India as a crucial factor in determining universities or college's ranking and recognition. A university's standing and reputation are greatly influenced by the number of students it places in jobs and the average compensation offered to those students. It would be extremely beneficial to develop Deep Learning (DL)-based algorithms that can assist individuals in getting placement guidance, analyses labor market trends, and help educational institutions evaluate opportunities and expanding fields. Numerous realistic and potential placement criteria, such as the kinds of organizations a junior year student can be put in or the companies that are likely to seek out a student's particular skill sets, can be estimated with the use of a DL model based on Predictive Analysis (PA). The Objectives can be predicted using a variety of characteristics, including projects, technical proficiency, training experiences, and academic performance. Initially, pre-processing is applied on the student placement dataset using K-Means Clustering (KMC) algorithm which handles the Missing Values (MV) and error values efficiently. Then, Enhanced Butterfly optimization algorithm (EBOA) is used to select the best students for placement based on their qualities. It is done by generating the optimal Fitness Values (FV). At last, the DL algorithm Improved Long Short-Term Memory (ILSTM) is used for predicting student placement and the results are superior. It is used to assist students and educational institutions in navigating the multifaceted landscape of placement prediction. Finding pupils with academic potential is assisted by this study. Their prospects of getting a placement are increased because this course allows students to concentrate on and develop their social and technical abilities. From the result, it proved that the suggested ILSTM based DL algorithm gives superior performance by means of greater Accuracy (Acc), Precision (P), Recall (R) and f-measure rather than the existing algorithms.
|
|---|---|
| ISSN: | 2583-6471 |