Bibliographic citations
Garcia, V., Garcia, G. (2023). Sistema de detección de desviación contable utilizando Machine Learning en empresas que cotizan en la Bolsa de Valores de Lima [Trabajo de Suficiencia Profesional, Universidad Peruana de Ciencias Aplicadas (UPC)]. http://hdl.handle.net/10757/671541
Garcia, V., Garcia, G. Sistema de detección de desviación contable utilizando Machine Learning en empresas que cotizan en la Bolsa de Valores de Lima [Trabajo de Suficiencia Profesional]. PE: Universidad Peruana de Ciencias Aplicadas (UPC); 2023. http://hdl.handle.net/10757/671541
@misc{renati/412679,
title = "Sistema de detección de desviación contable utilizando Machine Learning en empresas que cotizan en la Bolsa de Valores de Lima",
author = "Garcia Perez, Glenn Alan",
publisher = "Universidad Peruana de Ciencias Aplicadas (UPC)",
year = "2023"
}
At present, Peruvian banks review financial statements for granting loans, renewing lines of credit, among other financial products. Banking sector specialists conduct this activity to perform an analysis of the business, based on the financial information presented by the entities in their audited financial statements. This analysis requires accuracy and veracity of financial information. Experienced auditors perform their review based on their professional judgment, expertise, knowledge of the client, business, accounting policies and related standards. An organization listed on the Lima Stock Exchange may have millions of entries and the task of identifying where the audit risk may come from is like looking for a needle in a haystack. Machine learning algorithms allow us to detect accounting deviation with up to 98.09% and can be a potential support tool to help audit with greater accuracy. In this research work, a support tool was developed that allows banking sector specialists to identify trends and anomalies in the financial statements so that they can focus their efforts and minimize the risk of non-detection by auditors of accounting deviations. The solution that was implemented is based on a machine learning algorithm, to identify the appropriate one, the one with the best performance when detecting the accounting deviation was sought. The algorithm selected was Random Forest because of its high degree of accuracy that reduces the risk of non-detection. For the training of this intelligent system, we used public financial data of listed companies such as financial statements, income statements, among others.
This item is licensed under a Creative Commons License