Student Placement Prediction and Analysis using Machine Learning

Almost every student wishes to grab placement opportunity before completing their degree. There are various developing and developed placement opportunities in the market. However, a student must carefully choose his field and skills to satisfy the requirements set by employer. A placement prediction model helps students predict the probability of him/her being placed or not based on his academic and personal achievements. The K-Nearest Neighbors [KNN] algorithm, Decision tree, Logistic regression, Naïve Bayes, and Random Forest are the five distinct machine learning classification techniques that were considered for this project. These algorithms each independently forecast the outcomes, and we compare their efficacy based on the dataset. This prediction model can forecast the likelihood of the student being placed based on his qualification and work experience. Such prediction models could aid in a student’s or an institution’s future academic planning.