Student Employment Forecasting and Evaluation

Abstract

Campus placement is of significant importance to both students and educational institutions. Students aim to secure placements in reputable companies, making it a primary objective. Admission in many institutes is often influenced by the placement opportunities they offer undergraduates. This study focuses on predicting whether a student will be placed early on, providing insight to guide further actions towards securing a placement. Such forecasting can ultimately reduce the workload of the training and placement cell—our research centres on predicting the placement of undergraduates in specific companies. We conducted thorough data pre-processing to eliminate redundant features. Various machine learning models were employed, including logistic regression, SVM classification, decision tree classifier, random forest classifier, and k-NN classification. By utilizing historical placement data and using advanced ML techniques like regression analysis, classification algorithms, and ensemble methods, the proposed system will provide actionable insights to optimize the matching process between students and recruiters.