Student Placement Probabilistic Assessment Using Emotional Quotient With Machine Learning: A Conceptual Case Study

Abstract

The primary goal of the proposed study is to measure a student's Emotional Quotient (EQ) for job placement and to correlate the EQ with the ability of the student to survive in the industry. EQ is expected to be influenced by several demographic factors such as age, gender, academic performance, location, parental education, parental income, and family structure. However, the previous studies did not consider these factors. To validate the correlation of demographic factors with EQ, developed a data set considering the above-mentioned factors followed by designing several Machine Learning (ML) based ensemble techniques. Ratings for each parameter ranged from 1 to 10. Based on that, evaluating the results to choose the best approach. The primary goal of this inquiry was to identify the factors other than academic performance that prompt a student to get hired by a company more quickly. The final grade for all students is determined by ascertaining a student's emotional and intellectual ability. The fundamental contribution of this study is the establishment of a student's emotional calculation, along with an explanation of how to evaluate it, the advantages of such a concept, its psychometric validity, and its difficulties. The background and variety of validation studies will show how measurements can accurately and rigorously evaluate the behavioral level of EQ.