From academia to industry: A framework to securely implement big data and AI to predict college graduates' employment trajectories

Muhammad Faizan 1, *, Qiming Huang 1, Nayab Riaz 2 and Usman Saif 1

1 School of Computer and Communication Engineering, University of Science and Technology Beijing, Beijing, P.R. China.
2 School of Management Science and Engineering, University of Science and Technology Beijing, Beijing, P.R. China.
 
Research Article
International Journal of Science and Research Archive, 2024, 11(02), 708–723.
Article DOI: 10.30574/ijsra.2024.11.2.0497
Publication history: 
Received on 13 February 2024; revised on 22 March 2024; accepted on 25 March 2024
 
Abstract: 
The transition from academia to industry can be unpredictable, but what if we could forecast college graduate employment outcomes with both accuracy and robust security? This study introduces an innovative framework that leverages secure data analysis and machine learning to predict the employment trajectories of college graduates. By integrating homomorphic encryption, we safeguard the privacy of sensitive personal and academic data while enabling complex machine learning operations. Our approach involves meticulous data collection, feature engineering, encryption, and model development, resulting in a robust model that addresses privacy concerns without sacrificing prediction accuracy. We demonstrate our model's superiority over traditional approaches, achieving a notable increase in both security and stability.  This research illuminates the potential of encrypted data analysis in reshaping predictive modeling methods, offering insights for educational institutions, policymakers, and students. Our findings not only address a pressing issue in employment forecasting but also lay the groundwork for secure and ethical big data applications across various domains.
 
Keywords: 
Secure Data Analytics; Privacy-Preserving AI; Homomorphic Encryption; Employment Forecasting; Educational Analytics
 
Full text article in PDF: 
 
Copyright information: 

Copyright © 2024 Author(s) retain the copyright of this article. This article is published under the terms of the Creative Commons Attribution Liscense 4.0