{"about":{"site":"https://codewithpapers.app","non_affiliation":"Code with Papers and Syntology are not affiliated with, endorsed by, or sponsored by Papers with Code, Meta, or the pwc-archive mirror.","licence":"CC BY-SA 4.0","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","attribution":"https://codewithpapers.app/attribution","modified":"archive material modified by Syntology; see the attribution page"},"url":"/paper/detection-of-anomalies-in-large-scale","title":"Detection of Anomalies in Large Scale Accounting Data using Deep Autoencoder Networks","arxiv_id":"1709.05254","date":"2017-09-15","proceeding":null,"authors":["Marco Schreyer","Timur Sattarov","Damian Borth","Andreas Dengel","Bernd Reimer"],"abstract":"Learning to detect fraud in large-scale accounting data is one of the\nlong-standing challenges in financial statement audits or fraud investigations.\nNowadays, the majority of applied techniques refer to handcrafted rules derived\nfrom known fraud scenarios. While fairly successful, these rules exhibit the\ndrawback that they often fail to generalize beyond known fraud scenarios and\nfraudsters gradually find ways to circumvent them. To overcome this\ndisadvantage and inspired by the recent success of deep learning we propose the\napplication of deep autoencoder neural networks to detect anomalous journal\nentries. We demonstrate that the trained network's reconstruction error\nobtainable for a journal entry and regularized by the entry's individual\nattribute probabilities can be interpreted as a highly adaptive anomaly\nassessment. Experiments on two real-world datasets of journal entries, show the\neffectiveness of the approach resulting in high f1-scores of 32.93 (dataset A)\nand 16.95 (dataset B) and less false positive alerts compared to state of the\nart baseline methods. Initial feedback received by chartered accountants and\nfraud examiners underpinned the quality of the approach in capturing highly\nrelevant accounting anomalies.","url_abs":"http://arxiv.org/abs/1709.05254v2","url_pdf":"http://arxiv.org/pdf/1709.05254v2.pdf","source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","row_kind":"abstracts"},"code_links":[{"paper_slug":"detection-of-anomalies-in-large-scale","repo_url":"https://github.com/GitiHubi/deepAI","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"unanswered"}},{"paper_slug":"detection-of-anomalies-in-large-scale","repo_url":"https://github.com/koenvandevelde/fd-autoencoder","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"tf","reach":{"status":"unanswered"}},{"paper_slug":"detection-of-anomalies-in-large-scale","repo_url":"https://github.com/najibullohasror/Fraud-detection-on-accounting-financial-systems","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"none","reach":{"status":"unanswered"}},{"paper_slug":"detection-of-anomalies-in-large-scale","repo_url":"https://github.com/robeespi/Fraud-detection-on-accounting-financial-systems","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"none","reach":{"status":"unanswered"}}],"tasks":[{"task_slug":"attribute","task_name":"Attribute"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"syntology_url":"https://syntology.ai/paper/1709.05254","atlas_url":"https://app.syntology.ai/?focus=1709.05254","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}