Tools
Tools
Ayyam Perumal Rajan, Jeevan Kumar (2023) A Comprehensive Study of SMOTE-Enhanced Machine Learning Models on Learning Models on Credit Card Fraud Dataset. Masters thesis, Dublin, National College of Ireland.
Preview |
PDF (Master of Science)
Download (452kB) | Preview |
Preview |
PDF (Configuration manual)
Download (1MB) | Preview |
Abstract
Credit card fraud is a pervasive issue that puts both people and financial institutions at significant financial risk. Due to the increase in the number of online transactions, Effective and trustworthy fraud detection technologies are urgently needed. This study uses utilizing the Synthetic Minority Over-sampling Technique (SMOTE) to examine the productivity before and after balancing.
The results of the study show the differing degrees of efficiency reported among the various approaches. Notably, after class balancing, certain models demonstrated improved performance. This work serves as a compelling reminder of the importance of selecting proper machine learning techniques and preprocessing processes with care. These measures are critical in building robust fraud detection systems capable of withstanding the ever-changing landscape of fraudulent operations.
| Item Type: | Thesis (Masters) |
|---|---|
| Supervisors: | Name Email Byrne, Brian UNSPECIFIED |
| Uncontrolled Keywords: | Credit card fraud detection; SMOTE (Synthetic Minority Over-sampling Technique); Machine learning algorithms; Class imbalance |
| Subjects: | H Social Sciences > HG Finance > Credit. Debt. Loans. H Social Sciences > HG Finance > Fintech T Technology > T Technology (General) > Information Technology > Fintech Q Science > Q Science (General) > Self-organizing systems. Conscious automata > Machine learning |
| Divisions: | School of Computing > Master of Science in FinTech |
| Depositing User: | Tamara Malone |
| Date Deposited: | 02 Aug 2024 10:28 |
| Last Modified: | 02 Aug 2024 10:28 |
| URI: | https://norma.ncirl.ie/id/eprint/7013 |
Actions (login required)
 |
View Item |