Classification for Imbalanced Credit Card Transaction Data
Faculty Mentor
Dan Li
Presentation Type
Poster
Start Date
5-8-2024 11:15 AM
End Date
5-8-2024 1:00 PM
Location
PUB NCR
Primary Discipline of Presentation
Computer Science
Abstract
It is important for the credit card companies to identify fraudulent transactions to avoid financial loss for the customers and the companies. The challenge of fraud detection lies in the imbalanced feature of transaction data which makes traditional classification algorithms infeasible. This research investigates the methodologies that are commonly employed to deal with imbalanced datasets. Specifically, over-sampling, under-sampling, and Synthetic Minority Over-sample Technique (SMOTE) are studied. In addition, to better understand the statistical features of the credit card transaction data, we implement a stream mining algorithm, DGIM, to analyze the occurrences of fraudulent transactions over sliding windows. This study contributes to the understanding of effective strategies for mitigating imbalanced datasets and enhancing fraud detection mechanisms in financial system.
Recommended Citation
Sun, Wen, "Classification for Imbalanced Credit Card Transaction Data" (2024). 2024 Symposium. 33.
https://dc.ewu.edu/srcw_2024/ps_2024/p2_2024/33
Creative Commons License
This work is licensed under a Creative Commons Attribution-NonCommercial-No Derivative Works 4.0 International License.
Classification for Imbalanced Credit Card Transaction Data
PUB NCR
It is important for the credit card companies to identify fraudulent transactions to avoid financial loss for the customers and the companies. The challenge of fraud detection lies in the imbalanced feature of transaction data which makes traditional classification algorithms infeasible. This research investigates the methodologies that are commonly employed to deal with imbalanced datasets. Specifically, over-sampling, under-sampling, and Synthetic Minority Over-sample Technique (SMOTE) are studied. In addition, to better understand the statistical features of the credit card transaction data, we implement a stream mining algorithm, DGIM, to analyze the occurrences of fraudulent transactions over sliding windows. This study contributes to the understanding of effective strategies for mitigating imbalanced datasets and enhancing fraud detection mechanisms in financial system.