Prediction of Employability of Engineering Graduates using Machine Learning Techniques

Abstract

The number of graduates that are produced from the higher education organizations are exponentially increasing which in turn creates the need for early prediction of employability of the students. As the world is moving towards digital adoption, acquisition of skills and enhancement of knowledge plays a vital role, but it is still practised and acquired in a traditional way. The intent is to address this issue by predicting the status of student's employability by considering various factors such as academic score and skill set the student needs to possess as defined by the companies in general using machine learning algorithms. The proposed work used various machine learning algorithms like Support vector machine, Naïve Bayes, Random forest, Bayesian classifier, Artificial neural network, Logistic regression, Gradient boosting and Xgboost for the first phase where the employability of the student was predicted along with the areas in which the student has to improve in order to be eligible for employability. For the final phase, random forest algorithm was used as it predicted the highest accuracy when compared to other algorithms and it predicted the List of companies that a student is eligible for, List of eligible students under a particular role, List of students eligible for a particular company, Generation of report about student's eligibility, Generation of report about percentage of eligibility under each role. This research would be helpful for all kinds of organizations such as government, private and corporations as well as educational organizations.