Creative Commons License
This work is licensed under a Creative Commons Attribution-Noncommercial-No Derivative Works 4.0 License.
Date of Graduation
Bachelor of Science (BS)
Department of Computer Science
Advancements in the modern age have brought many conveniences, one of those being credit cards. Providing an individual the ability to hold their entire purchasing power in the form of pocket-sized plastic cards have made credit cards the preferred method to complete financial transactions. However, these systems are not infallible and may provide criminals and other bad actors the opportunity to abuse them. Financial institutions and their customers lose billions of dollars every year to credit card fraud. To combat this issue, fraud detection systems are deployed to discover fraudulent activity after they have occurred. Such systems rely on advanced machine learning techniques and other supportive algorithms to detect and prevent fraud in the future. This work analyzes the various machine learning techniques for their ability to efficiently detect fraud and explores additional state-of-the-art techniques to assist with their performance. This work also proposes a generalized strategy to detect fraud regardless of a dataset's features or unique characteristics. The high performing models discovered through this generalized strategy lay the foundation to build additional models based on state-of-the-art methods. This work expands on the issues of fraud detection, such as missing data and unbalanced datasets, and highlights models that combat these issues. Furthermore, state-of-the-art techniques, such as adapting to concept drift, are employed to combat fraud adaptation.
Lovo, William, "Detecting credit card fraud: An analysis of fraud detection techniques" (2020). Senior Honors Projects, 2020-current. 86.