A hybrid semi-supervised approach for financial fraud detection
- Resource Type
- Conference
- Authors
- Liu, Jin-Miao; Tian, Jiang; Cai, Zhu-Xi; Zhou, Yue; Luo, Ren-Hua; Wang, Ran-Ran
- Source
- 2017 International Conference on Machine Learning and Cybernetics (ICMLC) Machine Learning and Cybernetics (ICMLC), 2017 International Conference on. 1:217-222 Jul, 2017
- Subject
- Computing and Processing
Robotics and Control Systems
Signal Processing and Analysis
Clustering algorithms
Algorithm design and analysis
Wires
IP networks
Mobile communication
Anomaly detection
Feature extraction
Fraud Detection
Isolation Forest
K-means Clustering
Semi-supervised Learning
- Language
- ISSN
- 2160-1348
In this paper, we create a semi-supervised methodology for financial fraud detection in bank wire transactions based on a clustering-based-isolation-forest (CBiForest) algorithm. To test this hybrid model, we experiment on wire transaction data of twelve months from China Everbright Bank. The result of abnormal users is proved to be reliable and outperforms other clustering algorithms. Furthermore, our model can be regarded as a huge improvement for traditional expert system in bank.