Title: Providing an open framework to facilitate tax fraud detection

Authors: Jean Prolhac; Christophe Gaie

Addresses: Paris-Saclay University, CentraleSupélec, Gif-sur-Yvette, Metz Rennes, France ' Centre Interministériel de Services Informatiques Relatifs aux Ressources Humaines, Paris, France

Abstract: In the present article, the authors propose a novel framework to optimise tax fraud detection. The framework is based on the construction of four successive layers: Modelling, Data sets, Algorithms and Interfaces. The fraud detection model relies on four parameters that enable the computation of four fraud indicators. The data sets are built using five open data sources provided by the French Statistics Department. Then, fraud detection is performed using different neural network and random forest algorithms whose performances are discussed. Thereafter a novel approach is proposed as tax files are assigned to auditors according to their experience and skills. Finally, the interfaces developed during the project are described and offer a simple manner to benefit from the proposed framework. As the framework is shared on a public repository, every researcher can now contribute to optimise fraud detection algorithms.

Keywords: artificial intelligence; neural networks; e-government; fraud detection; open framework.

DOI: 10.1504/IJCAT.2023.134069

International Journal of Computer Applications in Technology, 2023 Vol.73 No.1, pp.24 - 41

Received: 19 Oct 2022
Accepted: 19 Feb 2023
Published online: 10 Oct 2023 *

Full-text access for editors Full-text access for subscribers Purchase this article Comment on this article