A Placement Prediction System using k-nearest neighbors classifier

Abstract

In this paper, we propose a Placement Prediction System which predicts the probability of a undergrad student getting placed in an IT company by applying the machine learning model of k-nearest neighbors's classification. We also compare the results of the same against the results obtained from other models like Logistic Regression and SVM. To do so we consider the academic history of the student as well as their skill set like, programming skills, communication skills, analytical skills and team work, which are tested by the hiring companies during the recruitment process. The data that is used for this purpose is the Placement Statistics of PES Institute of Technology, Bangalore South Campus for the previous two academic batches.