Integration of Artificial Intelligence in Tax Administration
A Comparative and Multidimensional Analysis
DOI:
https://doi.org/10.22370/riace.2023.12.1.4115Keywords:
Tax Fraud, Artificial Intelligence, Tax Administration, Fraud DetectionAbstract
Tax fraud is a global problem that affects economies and tax systems worldwide. This has led to a relentless search for solutions to mitigate this issue. Thanks to the rapid growth of technology, it is possible to find tools that support these processes, especially in the current digital era where Artificial Intelligence (AI) and Machine Learning represent a great opportunity, through the creation of algorithms that allow detecting and predicting acts that constitute fraud in certain contexts. This study analyzed the implementation of artificial intelligence (AI) in tax administration to detect "tax fraud", using an international comparative approach. The methodology used was a documentary study, through the review of application cases with the aim of collecting relevant and updated information. The articles were obtained through scientific databases, mainly from WOS and SCOPUS. The inclusion criteria focused on scientific articles and case studies published in indexed journals and relevant conferences, excluding works that did not directly address the topics of interest of this research. It was possible to examine AI techniques such as neural networks and gradient boosting models, applied in various contexts, including Spain, Armenia, Rwanda, and in Latin America in Argentina. Both technological advances and ethical and legal challenges are highlighted. The analysis reveals the varied effectiveness of AI in fraud detection and highlights the need for technological adaptation and protection of taxpayers' rights.
Downloads
References
ACA. (2020). IA explicable: poner al usuario en el centro. Disponible en: https://www.accaglobal.com/gb/en/professional-insights/technology/Explainable_AI.
Baghdasaryan, V., Davtyan, H., Sarikyan, A., & Navasardyan, Z. (2022). Improving tax audit efficiency using machine learning: The role of taxpayer’s network data in fraud detection. Applied Artificial Intelligence, 36(1), 2012002.
Belle, Fille, Murorunkwere., Dominique, Haughton., Joseph, Nzabanita., Francis, Kipkogei., Ignace, Habimana, Kabano. (2023). Predicting tax fraud using supervised machine learning approach. African Journal of Science, Technology, Innovation and Development, 1-12. doi: 10.1080/20421338.2023.2187930
Castellón, Pamela (2012). Caracterización de Contribuyentes que Presentan Facturas Falsas al SII Mediante Técnicas de Data Mining. Revista Ingeniería de Sistemas, Volumen XXV, Universidad de Chile, Santiago, Chile.
Castellón, Pamela y Juan D. Velásquez (2011). Caracterización de Contribuyentes que Presentan Facturas Falsas al SII Mediante Técnicas de Data Mining. Universidad de Chile, Santiago, Chile.
DARPA, 2016. Anuncio amplio de la agencia Inteligencia artificial explicable (XAI). Disponible en: https://www.darpa.mil/attachments/DARPA-BAA-16-53.pdf
Didimo, W., Grilli, L., Liotta, G., Menconi, L., Montecchiani, F., & Pagliuca, D. (2020). Combining Network Visualization and Data Mining for Tax Risk Assessment. Ieee Access, 8, 16073-16086.
Evrim, Tan., Anthony, Simonofski., Thomas, Tombal., Bjorn, Kleizen., Mathias, Sabbe., Lucas, Bechoux., Pauline, Willem. (2023). Artificial intelligence and algorithmic decisions in fraud detection: An interpretive structural model. Data & policy, 5.
Faundez-Ugalde, A., Mellado-Silva, R., & Aldunate-Lizana, E. (2020). Use of artificial intelligence by tax administrations: An analysis regarding taxpayers' rights in Latin American countries. Computer Law & Security Review, 38, Article 105441.
Fayyad, U., PiatetskyShapiro, G., & Smyth, P. (1996). From data mining to knowledge discovery in databases. Ai Magazine, 17(3), 37-54.
Microsoft. (2021, Octubre 28). Analytics for fraud prevention and fraud detection in taxes.
Murorunkwere, B. F., Tuyishimire, O., Haughton, D., & Nzabanita, J. (2022). Fraud detection using neural networks: A case study of income tax. Future Internet, 14(6), 168.
Nivela-Cornejo M., Echeverría-Desiderio S., Otero- Agreda O. (2020). Estilos de aprendizajes e inteligencia artificial.
OCDE (2019). Tax Administration 2019: Comparative Information on OECD and other Advanced and Emergin. Extraido de: Tax Administration 2019 : Comparative Information on OECD and other Advanced and Emerging Economies | Tax Administration : Comparative Information on OECD and Other Advanced and Emerging Economies | OECD iLibrary (oecd-ilibrary.org)g Eco
OCDE. (2022).OCDE. Obtenido de PROYECCIÓN MUNDIAL. París, Francia. Extraído de: Proyección mundial – OECD https://www.oecd.org/acerca/miembros-y-socios
Pérez López, C., Delgado Rodríguez, M. J., & de Lucas Santos, S. (2019). Tax fraud detection through neural networks: An application using a sample of personal income taxpayers. Future Internet, 11(4), 86.
Saragih, A. H., Reyhani, Q., Setyowati, M. S., & Hendrawan, A. (2023). The potential of an artificial intelligence (AI) application for the tax administration system’s modernization: the case of Indonesia. Artificial Intelligence and Law, 31(3), 491-514.
Servicio de impuestos internos. (2023). Acciones de control aplicadas por el SII permitieron una recaudación de más de $922 mil millones durante 2022.
SII. (2023). DICCIONARIO BÁSICO TRIBUTARIO CONTABLE. Extraido de: https://www.sii.cl/diccionario_tributario/dicc_e.htm
Stankevicius, E., & Leonas, L. (2015). Hybrid approach model for prevention of tax evasion and fraud. Procedia-Social and Behavioral Sciences, 213, 383-389.
UNIDAD DE ANÁLISIS FINANCIERO (2021). Extraido de: https://www.uaf.cl/descargas/entidades/Cartilla2021.pdf
Downloads
Published
How to Cite
Issue
Section
License
This work is licensed under a Creative Commons Attribution-NonCommercial 4.0 International License.
Aquellos autores/as que tengan publicaciones con esta revista, aceptan los términos siguientes:- Los autores/as conservarán sus derechos de autor y garantizarán a la revista el derecho de primera publicación de su obra, el cuál estará simultáneamente sujeto a la Licencia de reconocimiento de Creative Commons (CC Reconocimiento 4.0) que permite a terceros compartir la obra siempre que se indique su autor y su primera publicación esta revista.
- Los autores/as podrán adoptar otros acuerdos de licencia no exclusiva de distribución de la versión de la obra publicada (p. ej.: depositarla en un archivo telemático institucional o publicarla en un volumen monográfico) siempre que se indique la publicación inicial en esta revista.
- Se permite y recomienda a los autores/as difundir su obra a través de Internet (p. ej.: en archivos telemáticos institucionales o en su página web) antes y durante el proceso de envío, lo cual puede producir intercambios interesantes y aumentar las citas de la obra publicada. (Véase El efecto del acceso abierto).
