Enhancing employability prediction using stack ensemble learning

Employability prediction has earned significant attention recently, with numerous studies leveraging machine learning techniques to identify key predictors of employability. Even though the preceding research primarily focused on individual machine learning algorithms, this article explores the ability of stack ensemble learning in enhancing employability prediction accuracy. Utilizing a comprehensive employability prediction dataset, we applied stack ensemble learning and assessed the execution of various machine learning algorithms. Our results show that stack ensemble model generally performs well in forecasting employability. This study impacts the existing literature by demonstrating the worth of stack ensemble learning in employability prediction. Future research can be directed towards examining professional characteristics sought by employers during recruitment, providing precious perspectives for stakeholders to enhance employability prospects.