On the Evaluation of Classification Methods Applied to Requests for Revision of Registered Debts

Helton Lima, Damires Fernandes, Thiago Moura, Daniel Sabóia

2021

Abstract

Tax management is a complex problem faced by governments around the world. In Brazil, in order to help solving problems in this area, data analytics has been increasingly used to support and enhance tax management processes. In this light, this work proposes an approach which uses supervised learning in order to classify requests of an administrative service. The requests at hand are named as Requests for Revision of Registered Debt (R3Ds). The service underlying such requests is offered by the Brazil’s National Treasury Attorney-General's Office and usually deals with a high volume of registrations. The experimental evaluation accomplished in this work presents some promising results. The obtained classification models present good levels of accuracy, area under ROC curve and recall. Four evaluation scenarios have been experimented, including imbalanced and balanced data. The Random Forest model achieves the best results in all the evaluated scenarios.

Paper Citation

in Harvard Style

Lima H., Fernandes D., Moura T. and Sabóia D. (2021). On the Evaluation of Classification Methods Applied to Requests for Revision of Registered Debts. In Proceedings of the 23rd International Conference on Enterprise Information Systems - Volume 1: ICEIS, ISBN 978-989-758-509-8, pages 335-342. DOI: 10.5220/0010498403350342

in Bibtex Style

@conference{iceis21,
author={Helton Lima and Damires Fernandes and Thiago Moura and Daniel Sabóia},
title={On the Evaluation of Classification Methods Applied to Requests for Revision of Registered Debts},
booktitle={Proceedings of the 23rd International Conference on Enterprise Information Systems - Volume 1: ICEIS,},
year={2021},
pages={335-342},
publisher={SciTePress},
organization={INSTICC},
doi={10.5220/0010498403350342},
isbn={978-989-758-509-8},
}

in EndNote Style

TY - CONF

JO - Proceedings of the 23rd International Conference on Enterprise Information Systems - Volume 1: ICEIS,
TI - On the Evaluation of Classification Methods Applied to Requests for Revision of Registered Debts
SN - 978-989-758-509-8
AU - Lima H.
AU - Fernandes D.
AU - Moura T.
AU - Sabóia D.
PY - 2021
SP - 335
EP - 342
DO - 10.5220/0010498403350342