Student Placement Analysis using Machine Learning
N. Divya, Sravya Namburu, Rajalakshmi Raja
Abstract
Every educational institution recognises the importance of campus placements in assisting the student in achieving their objectives. According to the criteria of the company, the analysis of the placements needs to created estimate the likelihood that students will be put in a particular organisation. The placement analysis uses a different number of parameters that can be used to evaluate the student’s skill level. While some criteria are based on university standards, others come from assessments made using the placement management system itself. By combining these data points, the analysis must correctly forecast whether the student will be hired by a company. Finding a classification method that would work for our data collection and be as accurate as possible was the challenge. The type of problem an algorithm must solve and the data collection it must use will determine the accuracy of the algorithm. In order to analyse the accuracy levels of each algorithm regarding our problem and data set, this study ultimately choose SVM, Random Forest, Decision Tree as Existing algorithms and Logistic Regression, KNN, Gradient Boosting Classifier as Proposed Algorithms. This study may use the results of this test to decide which method to apply when integrating our analysis into the placement analysis system.