Predicting Student Placement using PCA and Machine Learning Technique

Le résumé fourni par la source

Student placement plays a crucial role in educational institutions, as it is a factor measure to identify the performance of an institution. Timely identification of student’s CGPA range can reduce concerns about students’ academic life and it will help to improve success and avoid risks. Recently, there has been an upsurge in the use of machine learning techniques for prediction, this research focuses on random forest for student prediction. This paper focus on the prediction of student placements based on criteria like attendance, backlog, communication, programming skill, verbal and aptitude exam over more than 500 samples, then the PCA technique is used to reduce the dimensionality of the dataset and to pinpoint the key elements that influence the prediction of student placement.The most crucial elements that influence a student’s likelihood of finding employment after completing their studies can be determined. Used PCA to identify the most important features that contribute to the probability of pupil placement. PCA works by modifying the initial dataset to a fresh set of variables, and principal elements, which identify the most significant patterns and variations in the data to increase the accuracy. The random forest algorithm is then used to build a predictive model and achieved 97 percentage of accuracy,that is trained on the reduced feature set to Identify the probability of a student being assigned to a job.By simplifying the dataset and focusing on the most important factors that affect the prediction, this method has been demonstrated to increase the efficiency and accuracy of student placement prediction. It is crucial to remember that the Random Forest model’s accuracy depends on the calibre and relevance of the input data. Additionally, it’s crucial to make sure the model is applied ethically, fairly, and without any prejudice or discrimination.

Ce résumé expose les affirmations des auteurs. BNTIC ne l’interprète pas comme une validation indépendante des résultats.