DC Element | Wert | Sprache |
dc.contributor.author | Fukas, Philipp | |
dc.contributor.author | Menzel, Lukas | |
dc.contributor.author | Thomas, Oliver | |
dc.date.accessioned | 2024-01-04T10:28:13Z | - |
dc.date.available | 2024-01-04T10:28:13Z | - |
dc.date.issued | 2022 | |
dc.identifier.uri | http://osnascholar.ub.uni-osnabrueck.de/handle/unios/72844 | - |
dc.description | Cited by: 0; Conference name: 17th International Conference on Wirtschaftsinformatik, WI 2022; Conference date: 21 February 2022 through 23 February 2022; Conference code: 191912 | |
dc.description.abstract | While current machine learning methods can detect financial fraud more effectively, they suffer from a common problem: dataset imbalance, i.e. there are substantially more non-fraud than fraud cases. In this paper, we propose the application of generative adversarial networks (GANs) to generate synthetic fraud cases on a dataset of public firms convicted by the United States Securities and Exchange Commission for accounting malpractice. This approach aims to increase the prediction accuracy of a downstream logit, support vector machine (SVM), and eXtreme Gradient Boosting (XGBoost) classifier by training on a more well-balanced dataset. While the results indicate that a state-of-the-art machine learning model like XGBoost can outperform previous fraud detection models on the same data, generating synthetic fraud cases before applying a machine learning model does not improve performance. © 2022 17th International Conference on Wirtschaftsinformatik, WI 2022. All rights reserved. | |
dc.language.iso | en | |
dc.publisher | Association for Information Systems | |
dc.relation.ispartof | 17th International Conference on Wirtschaftsinformatik, WI 2022 | |
dc.subject | 'current | |
dc.subject | Adaptive boosting | |
dc.subject | Classification (of information) | |
dc.subject | Crime | |
dc.subject | Data Augmentation | |
dc.subject | Financial Auditing | |
dc.subject | Financial fraud | |
dc.subject | Fraud Detection | |
dc.subject | Generative Adversarial Networks | |
dc.subject | Learning systems | |
dc.subject | Machine Learning | |
dc.subject | Machine learning methods | |
dc.subject | Machine learning models | |
dc.subject | Machine-learning | |
dc.subject | Prediction accuracy | |
dc.subject | Securities and Exchange Commissions | |
dc.subject | Support vector machines | |
dc.title | Augmenting Data with Generative Adversarial Networks to Improve Machine Learning-Based Fraud Detection | |
dc.type | conference paper | |
dc.identifier.scopus | 2-s2.0-85172017387 | |
dc.identifier.url | https://www.scopus.com/inward/record.uri?eid=2-s2.0-85172017387&partnerID=40&md5=e83574366249431a660ab089c3ff1267 | |
dcterms.isPartOf.abbreviation | Int. Conf. Wirtschaftsinformatik, WI | |
local.import.remains | affiliations : Osnabrück University, Osnabrück, Germany; German Research Center for Artificial Intelligence, Osnabrück, Germany; Strategion GmbH, Osnabrück, Germany | |
local.import.remains | publication_stage : Final | |
crisitem.author.dept | FB 09 - Wirtschaftswissenschaften | - |
crisitem.author.deptid | fb09 | - |
crisitem.author.parentorg | Universität Osnabrück | - |
crisitem.author.netid | ThOl011 | - |