Optimizing Student Placement Through Cross-Platform Solutions

In the present era, there has been a notable increase in the number of Educational Institutions. The primary aim of higher education establishments is to support students in securing employment through their training and placement office. However, a major challenge currently faced is the assessment and enhancement of student performance. Our developed system is designed to tackle this challenge by analyzing students’ historical data, including their academic and extracurricular activities, and predicting their expected placement package. This system proves advantageous for both the institute and the students as it enables them to strategize and improve their performance prior to actual placement drives conducted by companies. We have gathered a real-time dataset comprising of more than 600 records from the training and placement office of Ramrao Adik Institute of Technology (RAIT) in Navi Mumbai, India, covering the past two years. The analysis of this dataset involved the utilization of well-known algorithms such as Random Forest Regression, Multilinear Regression, and Decision Tree Regression. Three distinct models were developed, and the most effective algorithm was chosen. The model was then saved using pickle and deployed on the cloud. With an accuracy rate exceeding 95% after conducting 10+ trials and experiments, it is evident that this system greatly assists the placement cell in identifying promising students and focusing on nurturing the essential skills for their success.