Bayesian Networks on Income Tax Audit Selection - A Case Study of Brazilian Tax Administration
Abstract
Tax administrations in most countries have more corporate and personal information than any other government office. Data mining techniques can be used in many different problems due to the large amount of tax returns received every year. In the present work we show an application of the Brazilian Tax Administration on using Bayesian networks to predict taxpayer behavior based on historical analysis of income tax compliance. More specifically, we tried to improve a previous risk-based audit selection which detects a large number of taxpayers as high risk. However, in its current form it identifies far more cases than the tax auditors can handle. Our first results are promising, considerably improving tax audit performance.
Cite
Text
da Silva et al. "Bayesian Networks on Income Tax Audit Selection - A Case Study of Brazilian Tax Administration." Conference on Uncertainty in Artificial Intelligence, 2016.Markdown
[da Silva et al. "Bayesian Networks on Income Tax Audit Selection - A Case Study of Brazilian Tax Administration." Conference on Uncertainty in Artificial Intelligence, 2016.](https://mlanthology.org/uai/2016/dasilva2016uai-bayesian/)BibTeX
@inproceedings{dasilva2016uai-bayesian,
title = {{Bayesian Networks on Income Tax Audit Selection - A Case Study of Brazilian Tax Administration}},
author = {da Silva, Leon Sólon and Rigitano, Henrique and Carvalho, Rommel Novaes and Souza, João Carlos Félix},
booktitle = {Conference on Uncertainty in Artificial Intelligence},
year = {2016},
pages = {14-20},
url = {https://mlanthology.org/uai/2016/dasilva2016uai-bayesian/}
}