Article Details

Abstract

Financial fraud seriously threatens the stability of financial markets, and the existing anti-fraud methods have the problems of singleness and inefficiency. Therefore, this paper constructs a financial transaction fraud recognition model based on the Ensemble Learning method, aiming to improve the fraud recognition effect. In the research, four basic models are constructed by Bagging and Boosting, and two models with better effects are selected by optimizing parameters. Subsequently, the Stacking method is used to conduct fusion training for the two models, which further improves the recognition rate of the model. The experimental results show that the fusion model has significant advantages in financial transaction fraud identification. Compared with the basic model, it has higher accuracy with different datasets, especially in dealing with complex fraud patterns and new means, showing higher accuracy and stability. This improved model method provides effective decision support for financial decision makers and relevant departments, and helps to improve the security of financial markets.

Keywords

Ensemble Learning; financial fraud; Boosting; Stacking

References

1. [1] XU J，CHEN D Y，CHAU M. Identifying Features for Detecting Fraudulent Loan Requests on P2P Platforms [C]//2016 IEEE Conference on Intelligence and Security Informatics (ISI).Tucson：IEEE，2016：79-84.
2. [2] Xia Pingfan Research on Intelligent Risk Prediction Method for Digital Financial Fraud [D]. Hefei: Hefei University of Technology, 2022
3. [3] Chen Jing, Wang Minghai, Jiang Hao, etc Laboratory Abnormal Electricity Usage Behavior Detection Using Stacking Heterogeneous Model Fusion [J]. Laboratory Research and Exploration, 2024, 43 (1): 231-237
4. [4] Ouyang Xiaoqin, Wang Qiuhua AdaBoost Algorithm Based on Improved Weight Updating and Selective Integration [J]. Software Guide, 2020, 19 (4): 257-262
5. [5] Wang Jun, Liu Sanmin, Liu Tao Selective ensemble data stream classification method based on ant colony optimization [J]. Journal of Changjiang University: Self Science Edition, 2017, 14 (5): 37-43+85-86
6. [6] Xu Xiaoyang, Ji Zhicheng Research on Selective Ensemble Extreme Learning Machine Classifier Modeling [J]. Computer Applications and Software, 2016, 33 (9): 279-283
7. [7] Wang Jin, Ran Qianyuan, Ding Ling, etc Bagging Selective Integrated Evolutionary Hardware DNA Microarray Data Classification Method [J]. High Tech Communications, 2013, 23 (12): 1236-1241
8. [8] Zhang Yanping, Cao Zhentian, Zhao Shu, etc A New Selective Ensemble Learning Method for Decision Trees [J]. Computer Engineering and Applications, 2010, 46 (17): 41-44
9. [9] ZHANG D，JIAO L C，BAI X，et al. A Robust Semi-Supervised SVM Via Ensemble Learning [J].Applied Soft Computing，2018，65：632-643.
10. [10] FENG X，ZHAO Y L，ZHANG M，et al. Ensemble Learning-Based Stability Improvement Method for Feature Selection Towards Performance Prediction [J].Journal of Manufacturing Systems，2024，74：55-67.
11. [11] IJEH V，MORSI W G. Smart Grid Cyberattack Types Classification: A Fine Tree Bagging-based Ensemble Learning Approach with Feature Selection [J/OL].Sustainable Energy，Grids and Networks，2024，38：101291[2024-08-20].https://www.sciencedirect.com/science/article/abs/pii/S2352467724000201?via%3Dihub.
12. [12] WANG M Y，QIAN Y Y，YANG Y D，et al. Improved Stacking Ensemble Learning Based on Feature Selection to Accurately Predict Warfarin Dose [J/OL].Frontiers in Cardiovascular Medicine，2024，10：1320938（2021-01-19）.https://doi.org/10.3389/fcvm.2023.1320938.
13. [13] MOON J H，YU J H，SOHN K A. An Ensemble Approach to Anomaly Detection Using High- and Low-variance Principal Components [J/OL].Computers and Electrical Engineering，2022，99：107773[2024-08-26].https://www.sciencedirect.com/science/article/abs/pii/S0045790622000714?via%3Dihub.
14. [14] HUANG D，LIU Z G，WU D. Research on Ensemble Learning-Based Feature Selection Method for Time-Series Prediction [J/OL].Applied Sciences，2023，14（1）：40（2023-12-20）.https://doi.org/10.3390/app14010040.
15. [15] NADIA N，MORTEZA R，MAHDI E. A New Evolutionary Ensemble Learning of Multimodal Feature Selection from Microarray Data [J].Neural Processing Letters，2023，55（5）：6753-6780.
16. [16] PARTHASARATHY G，DEVI S S. Ensemble Learning Based Collaborative Filtering with Instance Selection and Enhanced Clustering [J].Computers， Materials & Continua，2022，71（2）：2419-2434.

Funding

Hebei Social Science Fund Project (HB22SH011)

About the authors

Zheng Deming (1998-), male, Han ethnicity, from Putian, Fujian, is a master's student with a research focus on data policing technology; Li Sijia (1987-), female, Han ethnicity, from Nanchang, Jiangxi Province, lecturer, master's supervisor, PhD, research direction: online public opinion, big data analysis; Pan Yankai (2002-), male, Han ethnicity, from Changde, Hunan Province, undergraduate studies, research direction: data policing technology; Zheng Jianlong (2001-), male, Han ethnicity, from Yiwu, Zhejiang, is currently pursuing a master's degree in data policing technology.