Feature generation and contribution comparison for electronic fraud detection
Abstract Modern money transfer services are convenient, attracting fraudulent actors to run scams in which victims are deceived into transferring funds to fraudulent accounts. Machine learning models are broadly applied due to the poor fraud detection performance of traditional rule-based approaches...
| Main Authors: | , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Nature Portfolio
2022-10-01
|
| Series: | Scientific Reports |
| Online Access: | https://doi.org/10.1038/s41598-022-22130-2 |
| _version_ | 1811257041285545984 |
|---|---|
| author | Yen-Wu Ti Yu-Yen Hsin Tian-Shyr Dai Ming-Chuan Huang Liang-Chih Liu |
| author_facet | Yen-Wu Ti Yu-Yen Hsin Tian-Shyr Dai Ming-Chuan Huang Liang-Chih Liu |
| author_sort | Yen-Wu Ti |
| collection | DOAJ |
| description | Abstract Modern money transfer services are convenient, attracting fraudulent actors to run scams in which victims are deceived into transferring funds to fraudulent accounts. Machine learning models are broadly applied due to the poor fraud detection performance of traditional rule-based approaches. Learning directly from raw transaction data is impractical due to its high-dimensional nature; most studies construct features instead by extracting patterns from raw transaction data. Past literature categorizes these features into recency, frequency, monetary, and anomaly detection features. We use various machine learning algorithms to examine the performance of features in these four categories with real transaction data; we compare them with the performance of our feature generation guideline based on the statistical perspectives and characteristics of (non)-fraudulent accounts. The results show that except for the monetary category, other feature categories used in the literature perform poorly regardless of which machine learning algorithm is used; anomaly detection features perform the worst. We find that even statistical features generated based on financial knowledge yield limited performance on a real transaction dataset. Our atypical detection characteristic of normal accounts improves the ability to distinguish them from fraudulent accounts and hence improves the overall detection results, outperforming other existent methods. |
| first_indexed | 2024-04-12T17:50:20Z |
| format | Article |
| id | doaj.art-c0d692c5b62542a48bd0a54e247517e3 |
| institution | Directory Open Access Journal |
| issn | 2045-2322 |
| language | English |
| last_indexed | 2024-04-12T17:50:20Z |
| publishDate | 2022-10-01 |
| publisher | Nature Portfolio |
| record_format | Article |
| series | Scientific Reports |
| spelling | doaj.art-c0d692c5b62542a48bd0a54e247517e32022-12-22T03:22:31ZengNature PortfolioScientific Reports2045-23222022-10-0112111110.1038/s41598-022-22130-2Feature generation and contribution comparison for electronic fraud detectionYen-Wu Ti0Yu-Yen Hsin1Tian-Shyr Dai2Ming-Chuan Huang3Liang-Chih Liu4College of Artificial Intelligence, Yango UniversityInstitute of Finance, National Yang Ming Chiao Tung UniversityDepartment of Information Management and Finance and Institute of Finance, National Yang Ming Chiao Tung UniversityInstitute of Computer Science and Engineering, National Yang Ming Chiao Tung UniversityDepartment of Information and Finance Management, National Taipei University of TechnologyAbstract Modern money transfer services are convenient, attracting fraudulent actors to run scams in which victims are deceived into transferring funds to fraudulent accounts. Machine learning models are broadly applied due to the poor fraud detection performance of traditional rule-based approaches. Learning directly from raw transaction data is impractical due to its high-dimensional nature; most studies construct features instead by extracting patterns from raw transaction data. Past literature categorizes these features into recency, frequency, monetary, and anomaly detection features. We use various machine learning algorithms to examine the performance of features in these four categories with real transaction data; we compare them with the performance of our feature generation guideline based on the statistical perspectives and characteristics of (non)-fraudulent accounts. The results show that except for the monetary category, other feature categories used in the literature perform poorly regardless of which machine learning algorithm is used; anomaly detection features perform the worst. We find that even statistical features generated based on financial knowledge yield limited performance on a real transaction dataset. Our atypical detection characteristic of normal accounts improves the ability to distinguish them from fraudulent accounts and hence improves the overall detection results, outperforming other existent methods.https://doi.org/10.1038/s41598-022-22130-2 |
| spellingShingle | Yen-Wu Ti Yu-Yen Hsin Tian-Shyr Dai Ming-Chuan Huang Liang-Chih Liu Feature generation and contribution comparison for electronic fraud detection Scientific Reports |
| title | Feature generation and contribution comparison for electronic fraud detection |
| title_full | Feature generation and contribution comparison for electronic fraud detection |
| title_fullStr | Feature generation and contribution comparison for electronic fraud detection |
| title_full_unstemmed | Feature generation and contribution comparison for electronic fraud detection |
| title_short | Feature generation and contribution comparison for electronic fraud detection |
| title_sort | feature generation and contribution comparison for electronic fraud detection |
| url | https://doi.org/10.1038/s41598-022-22130-2 |
| work_keys_str_mv | AT yenwuti featuregenerationandcontributioncomparisonforelectronicfrauddetection AT yuyenhsin featuregenerationandcontributioncomparisonforelectronicfrauddetection AT tianshyrdai featuregenerationandcontributioncomparisonforelectronicfrauddetection AT mingchuanhuang featuregenerationandcontributioncomparisonforelectronicfrauddetection AT liangchihliu featuregenerationandcontributioncomparisonforelectronicfrauddetection |