Efficient Student Profession Prediction Using XGBoost Algorithm

Abstract

As Competition is growing high students need to assess their capabilities and area of interest and plan their career from initial stages. Choosing a right profession is a crucial thing in today’s world. This paper proposes a Supervised Machine Learning Model which uses large number of datasets to train the model and predict the right career path for the students. The dataset is collected by evaluating the students and also by enabling the students to answer a set of questions. The dataset includes various parameters like students ability in academics, competition, programming languages, interested domain. Prediction of both academic performance and employability can help the management identify students at risk of poor academic performance and low employability Also recruiters use this model to recruit candidates and decide which job role to assign them based on their capabilities. This paper concentrates on scholar profession prediction of computer science candidates.