Feature Engineering and Resampling Strategies for Fund Transfer Fraud With Limited Transaction Data and a Time-Inhomogeneous Modi Operandi
Detecting financial fraud to profile crimes and pinpoint system vulnerabilities is an essential issue in the financial industry. Because of interpretability requirements and the lack of mass transaction data due to privacy regulations, sophisticated handcrafted features have been adopted in much of...
| Main Authors: | , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
IEEE
2022-01-01
|
| Series: | IEEE Access |
| Subjects: | |
| Online Access: | https://ieeexplore.ieee.org/document/9858047/ |
| _version_ | 1811339583104745472 |
|---|---|
| author | Yu-Yen Hsin Tian-Shyr Dai Yen-Wu Ti Ming-Chuan Huang Ting-Hui Chiang Liang-Chih Liu |
| author_facet | Yu-Yen Hsin Tian-Shyr Dai Yen-Wu Ti Ming-Chuan Huang Ting-Hui Chiang Liang-Chih Liu |
| author_sort | Yu-Yen Hsin |
| collection | DOAJ |
| description | Detecting financial fraud to profile crimes and pinpoint system vulnerabilities is an essential issue in the financial industry. Because of interpretability requirements and the lack of mass transaction data due to privacy regulations, sophisticated handcrafted features have been adopted in much of the literature for fraud detection. In addition to established recency, frequency, monetary, and anomaly features, we propose behavior- and segmentation-type features based on statistical characteristics belonging solely to (non-)fraudulent accounts informed by financial expertise. Our proposed features are difficult for automatic feature generators to synthesize, and provide transparent cause-effect relationships and good prediction results. Features with time-inhomogeneous properties cause popular boosting classifiers such as XGBoost and LGBM to produce unstable detection results. We use the Kolmogorov–Smirnov test to detect and remove these features to improve XGBoost and LGBM detection performance and robustness. The resulting performance shown in our experiments is better than that of other classifiers, such as SVM and random forests. We examine the advantage of our technique by comparing it with several feature engineering works on fraud detection and automatic feature generation methods. On the other hand, we also find that generating training/testing sets with random sampling falsely eliminates such time inhomogeneity and results in misleading assessments of the robustness of machine learning models. These time-inhomogeneous phenomena also entail various modus operandi patterns, which influence the performance of different resampling methods for addressing data imbalance in fraud detection. Improper linear interpolation of SMOTE-related approaches leads to poor performance due to varying patterns of modi operandi. However, synthesizing fraudulent samples with simple oversampling and GANs mitigates this problem. |
| first_indexed | 2024-04-13T18:28:59Z |
| format | Article |
| id | doaj.art-c48825e9994043bc83536d3197e95b0e |
| institution | Directory Open Access Journal |
| issn | 2169-3536 |
| language | English |
| last_indexed | 2024-04-13T18:28:59Z |
| publishDate | 2022-01-01 |
| publisher | IEEE |
| record_format | Article |
| series | IEEE Access |
| spelling | doaj.art-c48825e9994043bc83536d3197e95b0e2022-12-22T02:35:10ZengIEEEIEEE Access2169-35362022-01-0110861018611610.1109/ACCESS.2022.31994259858047Feature Engineering and Resampling Strategies for Fund Transfer Fraud With Limited Transaction Data and a Time-Inhomogeneous Modi OperandiYu-Yen Hsin0Tian-Shyr Dai1https://orcid.org/0000-0002-9226-3056Yen-Wu Ti2https://orcid.org/0000-0002-9834-0075Ming-Chuan Huang3Ting-Hui Chiang4Liang-Chih Liu5https://orcid.org/0000-0002-2594-0109Institute of Finance, National Yang Ming Chiao Tung University, Hsinchu, TaiwanDepartment of Information Management and Finance, National Yang Ming Chiao Tung University, Hsinchu, TaiwanCollege of Artificial Intelligence, Yango University, Fuzhou, ChinaInstitute of Computer Science and Engineering, National Yang Ming Chiao Tung University, Hsinchu, TaiwanDepartment of Information Engineering and Computer Science, Feng Chia University, Taichung, TaiwanDepartment of Information and Finance Management, National Taipei University of Technology, Taipei, TaiwanDetecting financial fraud to profile crimes and pinpoint system vulnerabilities is an essential issue in the financial industry. Because of interpretability requirements and the lack of mass transaction data due to privacy regulations, sophisticated handcrafted features have been adopted in much of the literature for fraud detection. In addition to established recency, frequency, monetary, and anomaly features, we propose behavior- and segmentation-type features based on statistical characteristics belonging solely to (non-)fraudulent accounts informed by financial expertise. Our proposed features are difficult for automatic feature generators to synthesize, and provide transparent cause-effect relationships and good prediction results. Features with time-inhomogeneous properties cause popular boosting classifiers such as XGBoost and LGBM to produce unstable detection results. We use the Kolmogorov–Smirnov test to detect and remove these features to improve XGBoost and LGBM detection performance and robustness. The resulting performance shown in our experiments is better than that of other classifiers, such as SVM and random forests. We examine the advantage of our technique by comparing it with several feature engineering works on fraud detection and automatic feature generation methods. On the other hand, we also find that generating training/testing sets with random sampling falsely eliminates such time inhomogeneity and results in misleading assessments of the robustness of machine learning models. These time-inhomogeneous phenomena also entail various modus operandi patterns, which influence the performance of different resampling methods for addressing data imbalance in fraud detection. Improper linear interpolation of SMOTE-related approaches leads to poor performance due to varying patterns of modi operandi. However, synthesizing fraudulent samples with simple oversampling and GANs mitigates this problem.https://ieeexplore.ieee.org/document/9858047/Electronic fund transfer fraud detectionfeature engineeringKolmogorov-Smirnov testresamplingfeature importance ranking |
| spellingShingle | Yu-Yen Hsin Tian-Shyr Dai Yen-Wu Ti Ming-Chuan Huang Ting-Hui Chiang Liang-Chih Liu Feature Engineering and Resampling Strategies for Fund Transfer Fraud With Limited Transaction Data and a Time-Inhomogeneous Modi Operandi IEEE Access Electronic fund transfer fraud detection feature engineering Kolmogorov-Smirnov test resampling feature importance ranking |
| title | Feature Engineering and Resampling Strategies for Fund Transfer Fraud With Limited Transaction Data and a Time-Inhomogeneous Modi Operandi |
| title_full | Feature Engineering and Resampling Strategies for Fund Transfer Fraud With Limited Transaction Data and a Time-Inhomogeneous Modi Operandi |
| title_fullStr | Feature Engineering and Resampling Strategies for Fund Transfer Fraud With Limited Transaction Data and a Time-Inhomogeneous Modi Operandi |
| title_full_unstemmed | Feature Engineering and Resampling Strategies for Fund Transfer Fraud With Limited Transaction Data and a Time-Inhomogeneous Modi Operandi |
| title_short | Feature Engineering and Resampling Strategies for Fund Transfer Fraud With Limited Transaction Data and a Time-Inhomogeneous Modi Operandi |
| title_sort | feature engineering and resampling strategies for fund transfer fraud with limited transaction data and a time inhomogeneous modi operandi |
| topic | Electronic fund transfer fraud detection feature engineering Kolmogorov-Smirnov test resampling feature importance ranking |
| url | https://ieeexplore.ieee.org/document/9858047/ |
| work_keys_str_mv | AT yuyenhsin featureengineeringandresamplingstrategiesforfundtransferfraudwithlimitedtransactiondataandatimeinhomogeneousmodioperandi AT tianshyrdai featureengineeringandresamplingstrategiesforfundtransferfraudwithlimitedtransactiondataandatimeinhomogeneousmodioperandi AT yenwuti featureengineeringandresamplingstrategiesforfundtransferfraudwithlimitedtransactiondataandatimeinhomogeneousmodioperandi AT mingchuanhuang featureengineeringandresamplingstrategiesforfundtransferfraudwithlimitedtransactiondataandatimeinhomogeneousmodioperandi AT tinghuichiang featureengineeringandresamplingstrategiesforfundtransferfraudwithlimitedtransactiondataandatimeinhomogeneousmodioperandi AT liangchihliu featureengineeringandresamplingstrategiesforfundtransferfraudwithlimitedtransactiondataandatimeinhomogeneousmodioperandi |