Electronic payment fraud detection using supervised and unsupervised learning
| dc.contributor.author | Pracidelli L.P. | |
| dc.contributor.author | Lopes F.S. | |
| dc.date.accessioned | 2024-03-12T23:50:08Z | |
| dc.date.available | 2024-03-12T23:50:08Z | |
| dc.date.issued | 2020 | |
| dc.description.abstract | © The Editor(s) (if applicable) and The Author(s), under exclusive license to Springer Nature Switzerland AG 2020.With the digital transformation over the years and the recent expansion made possible by the use of different applications, it can been seen the diversification of payments by electronic means that contributed to companies suffering even more from fraud, as well as the increase in payments made with the credit card that contributed to this growth. Fraud can been defined as an illegal activity applied with the intention of obtaining financial benefits without taking into consideration the consequences of this act. Thus, it was be proposed the construction of artifact capable of minimizing the problem using unsupervised and supervised algorithms based on machine learning techniques. The solution also considered mining techniques for data processing. The experiment used data from a company that operates private transport by application and relied on the knowledge of the company’s fraud specialist to identify existing frauds. K-means was be applied for grouping races with similar characteristics and after labeling in legitimate and fraudulent races, the performance of the SVM - support vector machine and ANN - artificial neural network algorithms for performance was compared. | |
| dc.description.firstpage | 88 | |
| dc.description.lastpage | 101 | |
| dc.description.volume | 1160 AISC | |
| dc.identifier.doi | 10.1007/978-3-030-45691-7_9 | |
| dc.identifier.issn | 2194-5365 | |
| dc.identifier.uri | https://dspace.mackenzie.br/handle/10899/35103 | |
| dc.relation.ispartof | Advances in Intelligent Systems and Computing | |
| dc.rights | Acesso Restrito | |
| dc.subject.otherlanguage | Data mining | |
| dc.subject.otherlanguage | Fraud identification | |
| dc.subject.otherlanguage | Machine learning | |
| dc.subject.otherlanguage | Supervised learning | |
| dc.subject.otherlanguage | Unsupervised learning | |
| dc.title | Electronic payment fraud detection using supervised and unsupervised learning | |
| dc.type | Artigo de evento | |
| local.scopus.citations | 0 | |
| local.scopus.eid | 2-s2.0-85086278894 | |
| local.scopus.subject | Artificial neural network algorithm | |
| local.scopus.subject | Digital transformation | |
| local.scopus.subject | Electronic payment | |
| local.scopus.subject | Financial benefits | |
| local.scopus.subject | Illegal activities | |
| local.scopus.subject | Private transport | |
| local.scopus.subject | Supervised algorithm | |
| local.scopus.subject | Supervised and unsupervised learning | |
| local.scopus.updated | 2024-05-01 | |
| local.scopus.url | https://www.scopus.com/inward/record.uri?partnerID=HzOxMe3b&scp=85086278894&origin=inward |