Predicting good fit students by correlating relevant personality traits with academic/career data

摘要

This paper discusses part of the main work in field of data science, mining and analytics. Family of algorithms is developed to predict the educational relevance of individuals' talents through lens of personality features (unstructured and semi-structured) and academic/career data. This paper presents progress of results in Good Fit Students (GFS) algorithms and math construct. This work addresses the problems of poor academic performances, low retention rates, drop outs, school transfers, costly readmissions, poor job performances, early job transfers and inefficient utilization/consideration of natural talents. GFS builds a framework and algorithms by correlating and blending social networking personality traits data with academic and career data. The results are promising at this stage of research and show improved predictions and relevant probabilities. Future work is focused on improving the results with more data and adding few more algorithms to the main research/framework.