Improving Tax Audit Efficiency Using Machine Learning: The Role of Taxpayer’s Network Data in Fraud Detection
Using the universe of Armenian business tax payers operating under a standard tax regime, we develop a fraud prediction model based on machine learning tools, with gradient boosting as the primary choice. Having to deal with broadly defined fraud and heterogeneous taxpayers, as well as a relatively...
| Main Authors: | , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Taylor & Francis Group
2022-12-01
|
| Series: | Applied Artificial Intelligence |
| Online Access: | http://dx.doi.org/10.1080/08839514.2021.2012002 |
| _version_ | 1797641065815080960 |
|---|---|
| author | Vardan Baghdasaryan Hrant Davtyan Arsine Sarikyan Zaruhi Navasardyan |
| author_facet | Vardan Baghdasaryan Hrant Davtyan Arsine Sarikyan Zaruhi Navasardyan |
| author_sort | Vardan Baghdasaryan |
| collection | DOAJ |
| description | Using the universe of Armenian business tax payers operating under a standard tax regime, we develop a fraud prediction model based on machine learning tools, with gradient boosting as the primary choice. Having to deal with broadly defined fraud and heterogeneous taxpayers, as well as a relatively small sample, we successfully derive important features from tax returns with a minimum of additional information. Among the important fraud predictors, we obtain historical fraud and audit, share of administrative costs, and external economic activity. We see two main contributions with generalizable practical implications for auditing authorities. First, by focusing on the lift score of the top decile, we demonstrate that even moderately accurate models can improve upon existing accuracy of rule-based approaches. Second, and more importantly, we demonstrate that the information contained in the supplier and buyer network of the taxpayer can be used whenever important predictors of fraud such as historical audits and fraud are not available. This is particularly important for situations with newly established companies, who would otherwise be under-rated in terms of fraud probability. |
| first_indexed | 2024-03-11T13:40:09Z |
| format | Article |
| id | doaj.art-3a25941f9da444fda9c8120cd3dcfb7e |
| institution | Directory Open Access Journal |
| issn | 0883-9514 1087-6545 |
| language | English |
| last_indexed | 2024-03-11T13:40:09Z |
| publishDate | 2022-12-01 |
| publisher | Taylor & Francis Group |
| record_format | Article |
| series | Applied Artificial Intelligence |
| spelling | doaj.art-3a25941f9da444fda9c8120cd3dcfb7e2023-11-02T13:36:37ZengTaylor & Francis GroupApplied Artificial Intelligence0883-95141087-65452022-12-0136110.1080/08839514.2021.20120022012002Improving Tax Audit Efficiency Using Machine Learning: The Role of Taxpayer’s Network Data in Fraud DetectionVardan Baghdasaryan0Hrant Davtyan1Arsine Sarikyan2Zaruhi Navasardyan3American University of ArmeniaAmerican University of Armenia, College of Business and EconomicsAmerican University of Armenia, Center for Business Research and DevelopmentAmerican University of Armenia, Center for Business Research and DevelopmentUsing the universe of Armenian business tax payers operating under a standard tax regime, we develop a fraud prediction model based on machine learning tools, with gradient boosting as the primary choice. Having to deal with broadly defined fraud and heterogeneous taxpayers, as well as a relatively small sample, we successfully derive important features from tax returns with a minimum of additional information. Among the important fraud predictors, we obtain historical fraud and audit, share of administrative costs, and external economic activity. We see two main contributions with generalizable practical implications for auditing authorities. First, by focusing on the lift score of the top decile, we demonstrate that even moderately accurate models can improve upon existing accuracy of rule-based approaches. Second, and more importantly, we demonstrate that the information contained in the supplier and buyer network of the taxpayer can be used whenever important predictors of fraud such as historical audits and fraud are not available. This is particularly important for situations with newly established companies, who would otherwise be under-rated in terms of fraud probability.http://dx.doi.org/10.1080/08839514.2021.2012002 |
| spellingShingle | Vardan Baghdasaryan Hrant Davtyan Arsine Sarikyan Zaruhi Navasardyan Improving Tax Audit Efficiency Using Machine Learning: The Role of Taxpayer’s Network Data in Fraud Detection Applied Artificial Intelligence |
| title | Improving Tax Audit Efficiency Using Machine Learning: The Role of Taxpayer’s Network Data in Fraud Detection |
| title_full | Improving Tax Audit Efficiency Using Machine Learning: The Role of Taxpayer’s Network Data in Fraud Detection |
| title_fullStr | Improving Tax Audit Efficiency Using Machine Learning: The Role of Taxpayer’s Network Data in Fraud Detection |
| title_full_unstemmed | Improving Tax Audit Efficiency Using Machine Learning: The Role of Taxpayer’s Network Data in Fraud Detection |
| title_short | Improving Tax Audit Efficiency Using Machine Learning: The Role of Taxpayer’s Network Data in Fraud Detection |
| title_sort | improving tax audit efficiency using machine learning the role of taxpayer s network data in fraud detection |
| url | http://dx.doi.org/10.1080/08839514.2021.2012002 |
| work_keys_str_mv | AT vardanbaghdasaryan improvingtaxauditefficiencyusingmachinelearningtheroleoftaxpayersnetworkdatainfrauddetection AT hrantdavtyan improvingtaxauditefficiencyusingmachinelearningtheroleoftaxpayersnetworkdatainfrauddetection AT arsinesarikyan improvingtaxauditefficiencyusingmachinelearningtheroleoftaxpayersnetworkdatainfrauddetection AT zaruhinavasardyan improvingtaxauditefficiencyusingmachinelearningtheroleoftaxpayersnetworkdatainfrauddetection |