TRAP@NCI

Implementation of Machine Learning Techniques to Predict Post-Collegiate Earnings & Student-Loan Repayment Prospects

Kariyedath, Vishnu Mohan (2017) Implementation of Machine Learning Techniques to Predict Post-Collegiate Earnings & Student-Loan Repayment Prospects. Masters thesis, Dublin, National College of Ireland.

[img]
Preview
PDF (Master of Science)
Download (1MB) | Preview

Abstract

In this age of self education and personalized unconventional learning, majority of people still see a college degree as a gateway to job the workforce and to enter their field of interest and this outlook does not seem to be disappearing. However, the burden of rising college tuition and increasing student-loan default rates raises concerns. A common belief that only prestigious, elite and expensive institutions can bring about attractive work life, is being debunked. There exists many institutions that do not belong the ivy league and does not have huge tuitions, but, their graduates end up quite successful. Due to the lack of relevant portals and resources that provide such data, it would make more sense to introduce such a practices in the market. This research paper presents a possible solution to this gap, by filling it with a prediction model that takes data from College Scorecard (US Department of education, US Census Bureau, etc) and provides estimation of possible future earning and their chances with student-loan debt repayment. The research makes use of multiple regression, Random Forest, XGBoost and Artificial Neural Networks to achieve this goal.

Item Type: Thesis (Masters)
Subjects: Q Science > QA Mathematics > Electronic computers. Computer science
T Technology > T Technology (General) > Information Technology > Electronic computers. Computer science

H Social Sciences > HG Finance > Credit. Debt. Loans.
H Social Sciences > HD Industries. Land use. Labor > Issues of Labour and Work > Classes of Labour > Graduate Employment
Divisions: School of Computing > Master of Science in Data Analytics
Depositing User: CAOIMHE NI MHAICIN
Date Deposited: 28 Aug 2018 11:05
Last Modified: 28 Aug 2018 11:05
URI: http://trap.ncirl.ie/id/eprint/3083

Actions (login required)

View Item View Item