A Data-Driven Probabilistic Machine Learning Study for Placement Prediction
Sachin Bhoite, Chandrashekhar H. Patil, Surabhi Thatte, Vikas Magar, Poonam Nikam
Abstract
Machine Learning (ML) technologies play a key role in improving the decision-making process involved in higher education sector. Campus placement not only affects a student's life but also the reputation of the institution. Each student dreams of working in an MNC (Multi-National Company) or any reputed company before leaving the institute and the institute also tries to place students in good company to escalate their reputation in society. Hence, this research work has attempted to develop an automatic system to predict the placement of students in the early stage of their education and positively impact the institute’s training and placement activity. Ensemble learning is the process of strategically generated multiple models, such as classifiers, and connect them to solve the computational complexity. Ensemble learning is primarily used to develop a model's categorization, indicator, function approximation, etc. and further act or humiliate the possibility of selecting a weak individual. The proposed strategy has attempted to address this problem statement. Furthermore, machine learning techniques such as Logistic Regression, Support Vector Machine, K-Nearest Neighbor, Decision Tree, Random Forest, and AdaBoost classifier are considered in this research study.