Correo Electrónico
DNINFOA - SIA
Bibliotecas
Convocatorias
Identidad U.N.
Publicado
Detection of anomalous transactions in a sugar company using Machine Learning models
Detección de transacciones anómalas en una empresa azucarera mediante modelos de aprendizaje automático
DOI:
https://doi.org/10.15446/dyna.v93n241.123727Palabras clave:
anomaly detection, unsupervised learning, financial data analytics, continuous auditing, sugar industry (en)detección de anomalías, aprendizaje no supervisado, analítica de datos financieros, auditoría continua, industria azucarera (es)
Descargas
The early detection of anomalous transactions is critical for preventing fraud and enhancing financial control within the agro-industrial sector. This research presents the design and implementation of a Machine Learning-based system for anomaly detection in the transactions of a Peruvian sugar company over the period 2022-2024. Unsupervised learning algorithms such as Isolation Forest, Local Outlier Factor, One-Class SVM, and Autoencoder were applied, and performance metrics for anomaly detection were compared, with One-Class SVM being the highest-scoring algorithm. The results highlight the potential of artificial intelligence to strengthen continuous audit processes and improve operational reliability in the Latin American agroindustrial context.
La detección temprana de transacciones anómalas es fundamental para prevenir el fraude y mejorar el control financiero en el sector agroindustrial. Esta investigación presenta el diseño y la implementación de un sistema basado en el aprendizaje automático para la detección de anomalías en las transacciones de una empresa azucarera peruana durante el período 2022-2024. Se aplicaron algoritmos de aprendizaje no supervisado, como Isolation Forest, Local Outlier Factor, One-Class SVM y Autoencoder, y se compararon las métricas de rendimiento para la detección de anomalías, siendo One-Class SVM el algoritmo con la puntuación más alta. Los resultados ponen de relieve el potencial de la inteligencia artificial para reforzar los procesos de auditoría continua y mejorar la fiabilidad operativa en el contexto agroindustrial latinoamericano.
Referencias
[1] Sun, Y., Li, J., Lu, M., and Guo, Z., Study of the Impact of the Big Data Era on Accounting and Auditing, 13(3), art. 07180, 2024. DOI: https://doi.org/10.48550/arXiv.2403.07180
[2] Association of Certified Fraud Examiners (ACFE), Occupational Fraud 2022: A Report to the Nations, [Online]. 2022. Available at: https://acfepublic.s3-us-west-2.amazonaws.com/2022+Report+to+the+Nations.pdf
[3] ECLAC, and FAO, Digitalization and technological change in agricultural and agro-industrial MSMEs in Latin America, [Online]. 2022. Available at: https://www.cepal.org/es/notas/digitalizacion-la-agroindustria-america-latina-caribe-avances-desafios-experiencias-la-cepal
[4] Hemati, H., Schreyer, M., and Borth, D., Continual learning for unsupervised anomaly detection in continuous auditing of financial accounting data, art. 13215, 2021. DOI: https://doi.org/10.48550/arXiv.2112.13215
[5] SUNAT, Tax compendium for students: tax code. 2022 financial year, [Online]. 2022. Available at: https://es.scribd.com/document/794910305/DT-Laws-2022-23
[6] ACFE, Executive fraud triangle, [Online]. 2015. Available at: https://www.acfe.com/fraud-magazine/all-issues/issue/article?s=2015-april-s2w-executive-fraud-triangle
[7] National Society of Industries (SNI), Informality in Ayacucho affects 9 out of 10 workers in the region, [Online]. 2022. Available at: https://sni.org.pe/informalidad-en-ayacucho-afecta-a-9-de-cada-10-trabajadores-de-la-region/
[8] Jaeho, T., Machine learning foundations: Supervised, Unsupervised, and Advanced Learning, art. 4, 2021. DOI: https://doi.org/10.1007/978-3-030-65900-4
[9] Hendaoui, S., and Zangar, N., Leveraging Unsupervised machine learning for new traffic types classification in hybrid satellite terrestrial network, pp. 1-5, art. 3662, 2023. DOI: https://doi.org/10.1109/ISNCC58260.2023.10323662
[10] Witten, I.H., Frank, E., Hall, M.A., and Pal, C.J., Data mining: practical machine learning tools and techniques, pp. 607-629, art. 5, 2011. DOI: https://doi.org/10.1016/C2009-0-19715-5.
[11] Herreros-Martínez, A., et al., Applied Machine learning to anomaly detection in enterprise purchase processes: a hybrid approach using clustering and isolation forest, 16(3), art. 177, 2025. DOI: https://doi.org/10.3390/info16030177
[12] Géron, A., Hands-On machine learning with scikit-learn, keras, and tensorflow, [Online]. 2019. Available at:https://www.amazon.com/Hands-Machine-Learning-Scikit-Learn-TensorFlow/dp/1098125975
[13] Pang, G., Shen, C., Cao, L., and van-den-Hengel, A., Deep learning for anomaly detection: a review, 50(29), pp. 1-38, 2020. DOI: https://doi.org/10.1145/3439950
[14] Schmidl, S., Naumann, F., and Papenbrock, T., AutoTSAD: Unsupervised Holistic Anomaly Detection for Time Series, 17(11), 2024. DOI: https://doi.org/10.14778/3681954.3681978
[15] Kumar, R., and Sharma, G., Rare event prediction: strategies for imbalanced datasets in anomaly detection, art. 439, 2024. DOI: https://doi.org/10.48550/arXiv.2412.13439
[16] Tian, H., Kong, H., Lu, S., and Li, K., Unsupervised anomaly detection of multivariate time series based on multi-standard fusion, 611, art. 128634, 2025. DOI: https://doi.org/10.1016/j.neucom.2024.128634
[17] Cao, Y., Xiang, H., Zhang, H., et al., Anomaly Detection based on isolation mechanisms: a survey, 22, pp. 849-865, 2025. DOI: https://doi.org/10.1007/s11633-025-1554-4.
[18] Flick, U., An Introduction to qualitative research, [Online]. 2022. Available at: https://www.amazon.com/-/es/Introduction-Qualitative-Research-Uwe-Flick/dp/1529781329
[19] Kimball, R., and Ross, M., The data warehouse toolkit: the definitive guide to dimensional modeling, [Online]. 2013. Available at: https://www.amazon.com/Data-Warehouse-Toolkit-Definitive-Dimensional/dp/1118530802
[20] The pandas development team, pandas, [Online]. 2020. Available at: https://pandas.pydata.org/
[21] Harris, C.R., et al., Array programming with NumPy, 585, pp. 357-362, 2020. DOI: https://doi.org/10.1038/s41586-020-2649-2
[22] Abadi, M., et al., TensorFlow: large-scale machine learning on heterogeneous distributed systems, art. 04467, 2015. DOI: https://doi.org/10.48550/arXiv.1603.04467
[23] Catalano, C., et al., Anomaly detection in smart agriculture systems, 143, 103750, 2022. DOI: https://doi.org/10.1016/j.compind.2022.103750
[24] Cheng, D., Zou, Y., Xiang, S., et al., Graph neural networks for financial fraud detection: a review, 19(199609), art. 40474, 2025. DOI: https://doi.org/10.1007/s11704-024-40474-y.
Cómo citar
IEEE
ACM
ACS
APA
ABNT
Chicago
Harvard
MLA
Turabian
Vancouver
Descargar cita
Licencia
Derechos de autor 2026 DYNA
Esta obra está bajo una licencia internacional Creative Commons Atribución-NoComercial-SinDerivadas 4.0.
El autor o autores de un artículo aceptado para publicación en cualquiera de las revistas editadas por la facultad de Minas cederán la totalidad de los derechos patrimoniales a la Universidad Nacional de Colombia de manera gratuita, dentro de los cuáles se incluyen: el derecho a editar, publicar, reproducir y distribuir tanto en medios impresos como digitales, además de incluir en artículo en índices internacionales y/o bases de datos, de igual manera, se faculta a la editorial para utilizar las imágenes, tablas y/o cualquier material gráfico presentado en el artículo para el diseño de carátulas o posters de la misma revista.
