Predicting Student Placement using Machine Learning Models: A Comparative Analysis

The transition from academia to the workforce marks a critical juncture for students, with the ability to predict their placement success becoming increasingly vital. This paper undertook a thorough comparative analysis of machine learning (ML) models applied in forecasting student placement. It delves into a range of factors influencing placement outcomes, encompassing academic performance, internship engagements, and demographic variables. Through an examination of the effectiveness of ML algorithms such as logistic regression, decision trees, random forests, and support vector machines, this study assesses their accuracy and efficacy in predicting student placements. The insights garnered from this analysis underscore the significance of internship experiences and academic achievements in shaping placement trajectories. Moreover, the research illuminates the crucial role of model selection and hyperparameter tuning in bolstering predictive capabilities. The findings gleaned from this study offer valuable insights into the intricate dynamics of student placement prediction, thereby aiding in the development of more precise and reliable ML models to assist students and educational institutions in navigating the multifaceted landscape of placement prediction. Throughout conducting this analysis Random Forest was found to be the most suitable prediction algorithm with over 81.47% accuracy in prediction placed and unplaced students. The dataset used had 2966 records which were collected from kaggle and various other sources or manually collected and converted into an csv file for conducting this analysis.