The Prediction of Application for Loan using Machine Learning Technique
Youngkeun Choi1, Jae Won Choi2
1Youngkeun Choi*, Division of Business Administration, Sangmyung University.
2Jae Won Choi, Department of Computer Science, University of Texas at Dallas.
Manuscript received on July 14, 2020. | Revised Manuscript received on July 27, 2020. | Manuscript published on August 10, 2020. | PP: 265-268 | Volume-9 Issue-10, August 2020 | Retrieval Number: 100.1/ijitee.J74280891020 | DOI: 10.35940/ijitee.J7428.0891020
Open Access | Ethics and Policies | Cite | Mendeley
© The Authors. Blue Eyes Intelligence Engineering and Sciences Publication (BEIESP). This is an open access article under the CC-BY-NC-ND license (http://creativecommons.org/licenses/by-nc-nd/4.0/)
Abstract: Machine learning techniques are used to verify the many kinds of loan prediction problems. This study pursue S two major goals. Firstly, this paper is to understand the role of variables in loan prediction modeling better. Secondly, the study evaluates the predictive performance of the decision trees. The corresponding variable information is drawn from a third-party website, international challenge on the popular internet platform Kaggle (www.kaggle.com), which provides data in the title of ‘Loan Prediction’ that was uploaded by Amit Parajapet. We used decision tree which is a powerful and popular machine learning algorithm to this date for predicting and classifying big data. Based on these results, first, women seem to be more likely to get to loan than men. credit history, self-employed, property area, and applicant income also show significance with loan prediction. This study contributes to the literature regarding loan prediction by providing a global model summarizing the loan prediction determinants of customers’ factors.
Keywords: Machine learning, Decision tree, Artificial intelligence, Financial service, Loan prediction.
Scope of the Article: Machine Learning