FRAUD PREDICTION IN BANK CREDIT ADMINISTRATION: A SYSTEMATIC LITERATURE REVIEW
| dc.contributor.author | EWEOYA, IBUKUN | |
| dc.contributor.author | ADEBIYI, AYODELE | |
| dc.contributor.author | AZETA, AMBROSE | |
| dc.contributor.author | OKESOLA, OLATUNJI | |
| dc.date.accessioned | 2021-09-23T10:54:10Z | |
| dc.date.available | 2021-09-23T10:54:10Z | |
| dc.date.issued | 2019-06 | |
| dc.description | Staff Publication | en_US |
| dc.description.abstract | Any business or organization that intends to be far from bankruptcy or crime strives daily to ensure crime perpetration does not occur in the organization unabated. Traditional methods of fraud detection in credit administration are available but limited in capacity to check current sophistication in fraud perpetration; those approaches did not offer the best for time-consumption and efficiency; also, frauds are better predicted rather than a detection after the deal is done. This work presents an extensive review of literature and related works in fraud prediction in credit administration. The primary focus of this research work is to identify and dwell on the major concepts and techniques used for financial fraud prediction in credit administration as well as related works that have been done in this domain of study; while the work recommends the ensemble approach as a better alternative in this domain. The existing systematic literature reviews in this domain are not in the context of credit fraud prediction alone. | en_US |
| dc.identifier.issn | 1817-3195 | |
| dc.identifier.uri | http://repository.elizadeuniversity.edu.ng/handle/20.500.12398/1246 | |
| dc.language.iso | en | en_US |
| dc.publisher | Journal of Theoretical and Applied Information Technology | en_US |
| dc.subject | Fraud, | en_US |
| dc.subject | Supervised learning, | en_US |
| dc.subject | Credit, | en_US |
| dc.subject | Ensemble, | en_US |
| dc.subject | Machine learning | en_US |
| dc.title | FRAUD PREDICTION IN BANK CREDIT ADMINISTRATION: A SYSTEMATIC LITERATURE REVIEW | en_US |
| dc.type | Article | en_US |