Student Placement Prediction System using Machine Learning

Abstract

This paper presents an overview of the machine learning techniques that can be used to predict a student’s placement performance. The ability to predicting the performance of a student is a very essential task of all educational institutions. Since this is the task of predicting student’s placement of undergraduate students. This paper can be used to predict the probability of an undergraduate student getting placed by applying different machine learning algorithms. In this system, multilayer perceptron (MLP), logistic model tree (LMT), sequential minimal optimization (SMO), simple logistic, and logistic classifiers are applied to predict student performance. These classifiers independently predict the results and then compare the accuracy of the algorithms, which is based on the data set. After performing analysis on different matrices (time taken to build classifier, correctly classified instances, root mean squared error, incorrectly classified instances, precision, recall, F-measure, ROC area) by different machine learning algorithms, we are able to find which algorithm is performing better than other on the student data set, so that we are able to make a guideline for future improvement of student placement performance in education.