Predicting Student Employability Using Machine Learning: A Comparative Study of Classification Algorithms

DOI

10.2991/978-94-6463-858-5_68How to use a DOI?

Keywords

Extreme Gradient Boosting (XGBoost); Random Forest (RF); Logistic Regression (LR)

Abstract

Student placements are now a crucial component in assessing the efficacy of educational institutions due to the heightened competition in the market. The dynamic nature of employment patterns, individual student talents, and industry expectations are frequently overlooked by traditional placement prediction algorithms, which rely on static cutoffs and historical trends. In order to overcome these obstacles, this study uses machine learning methods—Logistic Regression, Random Forest, and XGBoost—to forecast student placements according to technical proficiency, extracurricular involvement, and academic achievement. In this study, we dive into student profiles that include academic scores, projects, internships, certificates, extracurricular activities, and aptitude test results. Our goal isto build a prediction model that can accurately gauge a student’s chances of landing a job with a corporation. We start with logistic regression for its straightforward interpretability and to understand which features matter most. To enhance predictive accuracy, we turn to Random Forest, an ensemble learning method that helps reduce variance and uncover complex patterns in the data. For an extra boost, we employ XGBoost, a powerful gradient boosting algorithm that optimizes decision trees through parallel computing and regularization techniques. Our solution leverages Python-based machine learning frameworks like Scikit-learn and XGBoost for training and evaluating the models, while React.js powers an interactive user interface, and MongoDB handles efficient data storage and retrieval. To assess how well our models predict placement outcomes, we use standard performance metrics such as accuracy, precision, recall, and F1-score. After thorough testing and comparison, we find that XGBoost surpasses both Random Forest and Logistic Regression in prediction performance, achieving the highest accuracy and recall rates. Students can increase their employability and pinpoint important areas for growth with the aid of the insights this study has produced. These results can also be used by educational institutions to improve their training curricula, match industry demands to coursework, and provide focused career counselling. This study demonstrates the revolutionary potential of machine learning in placement prediction, providing a data-driven approach to improving job options for students and expediting recruitment processes for businesses.

Copyright

© 2025 The Author(s)

Open Access

Open Access This chapter is licensed under the terms of the Creative Commons Attribution-NonCommercial 4.0 International License (http://creativecommons.org/licenses/by-nc/4.0/), which permits any noncommercial use, sharing, adaptation, distribution and reproduction in any medium or format, as long as you give appropriate credit to the original author(s) and the source, provide a link to the Creative Commons license and indicate if changes were made.

Download article (PDF)

TY  - CONF
AU  - A. Durga Praveen Kumar
AU  - Vasuta Kuchhadia
AU  - Gedela Charan
AU  - Gyana Sreeja
AU  - Nimmala Pavan
PY  - 2025
DA  - 2025/11/04
TI  - Predicting Student Employability Using Machine Learning: A Comparative Study of Classification Algorithms
BT  - Proceedings of International Conference on Computer Science and Communication Engineering (ICCSCE 2025)
PB  - Atlantis Press
SP  - 799
EP  - 812
SN  - 2352-538X
UR  - https://doi.org/10.2991/978-94-6463-858-5_68
DO  - 10.2991/978-94-6463-858-5_68
ID  - Kumar2025
ER  -