Detection of Taxpayers with High Probability of Non-payment: An Implementation of a Data Mining Framework
José Ordoñez-Placencia, María Hallo, Sergio Luján-Mora
15th Iberian Conference on Information Systems and Technologies (CISTI 2020), p. 1-6, Seville (Spain), June 24-27 2020. ISBN: 978-989-54659-0-3. https://doi.org/10.23919/CISTI49556.2020.9140837
(CISTI'20)
Congreso internacional / International conference
Resumen
Due to limitations in tax administrations, such as: staff, tools, time, etc., tax administrations seek to recover debts in the early stages of control, where the cost of collection is lower than in the subsequent stages. This work proposes a framework based on deep learning techniques to predict debts of taxpayers with high probability of non-payment in a short period of time. A group of debts of a tax administration was used to generate the model to estimate the risk of non-payment. A concordance index metric was used to measure the performance. The performance obtained was 90%.