원문정보
초록
영어
This thesis proposes a method to detect financial fraud by dividing users’ financial transactions into a normal area and an abnormal area, using SVDD and train the areas as such fraud evolves in terms of complexity. The existing financial industry detects electronic financial frauds using FDS, but its false positive rate is high enough to require additional authentications of user information. It causes customers inconveniences and does not always detect those sophisticated financial frauds. In order to resolve the aforementioned issues, this study proposes a method to detect such potential frauds by profiling user financial transaction data including user activities, device information, and transaction patterns and vectorizing them into a normal area and an abnormal area using SVDD.
목차
1. Introduction
2. Data Profiling of Financial Transaction
2.1. Research Status of Detection of Financial Frauds
2.2. Financial Transaction User Action-based SVDD Profiling
3. Detection of User Financial Frauds using SVDD
3.1. Procedures to Detect Financial Frauds
4. Performance Evaluation of SVDD-based FDS
4.1. Evaluation Criteria
4.2. Evaluation Result
5. Conclusion
Acknowledgments
References