Detection of anomalous transactions in a sugar company using Machine Learning models
DYNA · 18.05.2026 · 93 (241) · 59-65
DOI: 10.15446/dyna.v93n241.123727 ↗Kurz gefasst
Fachartikel in der Zeitschrift DYNA, online erschienen am 18.05.2026. Verfasst von José Armando Avalos-Vasquez und 3 weiteren Autor:innen. Die Arbeit wurde bisher 1-mal zitiert (Crossref) und nennt 24 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY-NC-ND 4.0).
Abstract (Originalsprache)
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.
Zitieren
APA
Avalos-Vasquez, J. A., Saavedra-Machaca, L. A., Ogosi-Auqui, J. A., & Gaitan, E. H. P. (2026). Detection of anomalous transactions in a sugar company using Machine Learning models. DYNA, 93(241), 59-65. https://doi.org/10.15446/dyna.v93n241.123727
Vancouver
Avalos-Vasquez JA, Saavedra-Machaca LA, Ogosi-Auqui JA, Gaitan EHP. Detection of anomalous transactions in a sugar company using Machine Learning models. DYNA. 2026;93(241):59-65. doi:10.15446/dyna.v93n241.123727
BibTeX
@article{AvalosVasquez2026,
author = {Avalos-Vasquez, José Armando and Saavedra-Machaca, Luis Alberto and Ogosi-Auqui, José Antonio and Gaitan, Eduardo Humberto Poletti},
title = {Detection of anomalous transactions in a sugar company using Machine Learning models},
journal = {DYNA},
year = {2026},
volume = {93},
number = {241},
pages = {59--65},
doi = {10.15446/dyna.v93n241.123727}
}
EUVIMED