Developing a Predictive Model for Engineering Graduates Placement Using a Data-Driven Machine Learning Approach

This study presents a novel predictive model for engineering graduates' placement outcomes using Machine Learning (ML) techniques. The model is built on a comprehensive dataset that includes students' performance in various skill areas and their subsequent placement status. By employing a range of ML algorithms, the study evaluates their performance in terms of accuracy. The findings reveal the Customized Random Forest Model (CRFM) algorithm as the most accurate, with a prediction rate of 89%. Furthermore, the study also evaluates the target job domain or field in which students aim to secure placements as well as their target salary packages using the Customized Principal Component Analysis (CPCA) model. The research highlights the importance of various skills, such as programming, aptitude, and domain knowledge, in determining the employability of engineering graduates. The study underscores the importance of various skills, such as programming, aptitude, and domain knowledge, in determining the employability of engineering graduates. The proposed model has directed and practical implications for educational institutions, policymakers, and employers, enabling them to identify the key factors that influence the employability of engineering graduates and develop strategies to enhance their employability.