Placement Prediction Using Various Machine Learning Models And Their Efficiency Comparison

A placement predictor will be designed to calculate the likelihood of a student being hired by a company, based on the company’s criteria. The predictor uses various parameters to evaluate the student’s skill level. Some parameters come from the university, while others are gathered from tests conducted in the placement management system. By combining these data points, the predictor aims to accurately determine if a student will be placed in a company. Data from previous students will be used to train the predictor. However, the challenge was to find an effective classification algorithm that could achieve high accuracy with our data set. Different algorithms yield varying accuracy based onthe problem they address and the data they handle. Therefore, we chose four algorithms: KNN, SVM, Logistic Regression, and Random Forest. We will compare the accuracy of each algorithm in relation to our problem and data set. The results will guide us in choosing the best algorithm for implementing our predictor in the placement management system.