Detecting problematic transactions in a consumer-to-consumer e-commerce network
Abstract Providers of online marketplaces are constantly combatting against problematic transactions, such as selling illegal items and posting fictive items, exercised by some of their users. A typical approach to detect fraud activity has been to analyze registered user profiles, user’s behavior,...
| Main Authors: | , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
SpringerOpen
2020-11-01
|
| Series: | Applied Network Science |
| Subjects: | |
| Online Access: | http://link.springer.com/article/10.1007/s41109-020-00330-x |
| _version_ | 1819170116211834880 |
|---|---|
| author | Shun Kodate Ryusuke Chiba Shunya Kimura Naoki Masuda |
| author_facet | Shun Kodate Ryusuke Chiba Shunya Kimura Naoki Masuda |
| author_sort | Shun Kodate |
| collection | DOAJ |
| description | Abstract Providers of online marketplaces are constantly combatting against problematic transactions, such as selling illegal items and posting fictive items, exercised by some of their users. A typical approach to detect fraud activity has been to analyze registered user profiles, user’s behavior, and texts attached to individual transactions and the user. However, this traditional approach may be limited because malicious users can easily conceal their information. Given this background, network indices have been exploited for detecting frauds in various online transaction platforms. In the present study, we analyzed networks of users of an online consumer-to-consumer marketplace in which a seller and the corresponding buyer of a transaction are connected by a directed edge. We constructed egocentric networks of each of several hundreds of fraudulent users and those of a similar number of normal users. We calculated eight local network indices based on up to connectivity between the neighbors of the focal node. Based on the present descriptive analysis of these network indices, we fed twelve features that we constructed from the eight network indices to random forest classifiers with the aim of distinguishing between normal users and fraudulent users engaged in each one of the four types of problematic transactions. We found that the classifier accurately distinguished the fraudulent users from normal users and that the classification performance did not depend on the type of problematic transaction. |
| first_indexed | 2024-12-22T19:30:16Z |
| format | Article |
| id | doaj.art-4f73cd74f2c248cd8646d8c294d1a8e6 |
| institution | Directory Open Access Journal |
| issn | 2364-8228 |
| language | English |
| last_indexed | 2024-12-22T19:30:16Z |
| publishDate | 2020-11-01 |
| publisher | SpringerOpen |
| record_format | Article |
| series | Applied Network Science |
| spelling | doaj.art-4f73cd74f2c248cd8646d8c294d1a8e62022-12-21T18:15:08ZengSpringerOpenApplied Network Science2364-82282020-11-015111810.1007/s41109-020-00330-xDetecting problematic transactions in a consumer-to-consumer e-commerce networkShun Kodate0Ryusuke Chiba1Shunya Kimura2Naoki Masuda3Graduate School of Information Sciences, Tohoku UniversityMercari, Inc.Mercari, Inc.Department of Engineering Mathematics, University of BristolAbstract Providers of online marketplaces are constantly combatting against problematic transactions, such as selling illegal items and posting fictive items, exercised by some of their users. A typical approach to detect fraud activity has been to analyze registered user profiles, user’s behavior, and texts attached to individual transactions and the user. However, this traditional approach may be limited because malicious users can easily conceal their information. Given this background, network indices have been exploited for detecting frauds in various online transaction platforms. In the present study, we analyzed networks of users of an online consumer-to-consumer marketplace in which a seller and the corresponding buyer of a transaction are connected by a directed edge. We constructed egocentric networks of each of several hundreds of fraudulent users and those of a similar number of normal users. We calculated eight local network indices based on up to connectivity between the neighbors of the focal node. Based on the present descriptive analysis of these network indices, we fed twelve features that we constructed from the eight network indices to random forest classifiers with the aim of distinguishing between normal users and fraudulent users engaged in each one of the four types of problematic transactions. We found that the classifier accurately distinguished the fraudulent users from normal users and that the classification performance did not depend on the type of problematic transaction.http://link.springer.com/article/10.1007/s41109-020-00330-xNetwork analysisMachine learningFraud detectionComputational social science |
| spellingShingle | Shun Kodate Ryusuke Chiba Shunya Kimura Naoki Masuda Detecting problematic transactions in a consumer-to-consumer e-commerce network Applied Network Science Network analysis Machine learning Fraud detection Computational social science |
| title | Detecting problematic transactions in a consumer-to-consumer e-commerce network |
| title_full | Detecting problematic transactions in a consumer-to-consumer e-commerce network |
| title_fullStr | Detecting problematic transactions in a consumer-to-consumer e-commerce network |
| title_full_unstemmed | Detecting problematic transactions in a consumer-to-consumer e-commerce network |
| title_short | Detecting problematic transactions in a consumer-to-consumer e-commerce network |
| title_sort | detecting problematic transactions in a consumer to consumer e commerce network |
| topic | Network analysis Machine learning Fraud detection Computational social science |
| url | http://link.springer.com/article/10.1007/s41109-020-00330-x |
| work_keys_str_mv | AT shunkodate detectingproblematictransactionsinaconsumertoconsumerecommercenetwork AT ryusukechiba detectingproblematictransactionsinaconsumertoconsumerecommercenetwork AT shunyakimura detectingproblematictransactionsinaconsumertoconsumerecommercenetwork AT naokimasuda detectingproblematictransactionsinaconsumertoconsumerecommercenetwork |