Publication Date

Spring 5-4-2023

Document Type


Degree Name

Master of Science in Mathematics (MS)



Committee Chair

Dr. Saqib Hussain

Committee Member

Dr. Runchang Lin

Committee Member

Dr. Muhammad Mohebujjaman

Committee Member

Dr. Tariq H. Tashtoush


The question of accurately predicting credit card defaulters has been explored in numerous studies in the past. In these studies, the researchers utilized various machine learning theories and techniques to make the determination the extent of defaults. Unfortunately, some constraints were encountered, and the limitations that existed from the previous works have been discussed. This project attempted to address these issues with special attention given to more recently available data. Specifically, in this project, we looked at data provided by one Kaggle user, which utilized the data from the American Express credit card competition, which ranges from late March 2018 to late October 2019, approximately 18 months. The extent of credit card defaulters was looked into using the data and used a machine learning technique, called Extremely Randomized Trees. Furthermore, a balancing technique, called Synthetic Minority Oversampling Technique, also known as SMOTE, was used to ensure the classes that were explored and balanced. Finally, the findings from the current research were compared with that of previous findings. The outcome of this project was understanding and analyzing previous research utilizing the updated available data to predict credit card payment defaults more accurately.