An Analytical Assessment of Machine Learning Algorithms for Predicting Campus Placements

Abstract

Employability is critical in determining a country's growth. Predicting the employability rate will provide a framework for the government and economists to plan for the future, as well as education management to understand changing trends. As a result, in recent years, models to predict job admission have been developed. However, in order to increase employability, deficiencies in the educational system must be addressed. The goal of this project is to find the best-fit classifier model to assess educational data, which can then be used to understand the importance of academic parameters in a person getting a job during on-campus recruitment. This is accomplished by comparing four different types of classifier algorithms (ANN (Artificial Neural Network), AdaBoost Classifier, Random Forest, and Logistic Regression) for the created dataset.