,
Faculty of Economics, University of Belgrade , Belgrade , Serbia
Faculty of Economics, University of Belgrade , Belgrade , Serbia
Benford's law is a key tool for detecting irregularities and potential manipulations in numerical data sets. This law describes the probability of the appearance of the first digits in large sets of numerical values, which allows for the identification of anomalies and verification of authenticity in them. The subject of this paper is the application of artificial intelligence in the analysis and verification of Benford's law on real data. Given the increasingly widespread application of artificial intelligence in the automation of data analysis, fraud detection and statistical verification of economic and financial reports, the aim of the paper is to explore the possibilities of using machine learning algorithms, such as deep neural networks and classification methods, to recognize and analyze deviations from the expected distribution of the first digits. The use of artificial intelligence in the automation of the verification process and the detection of manipulations in data is also considered. The results show that the application of artificial intelligence can significantly improve the accuracy of anomaly detection, while at the same time enabling faster and more efficient analysis of large data sets. It is concluded that artificial intelligence is a powerful tool in improving the application of Benford's law in practical situations, especially in the analysis of financial and other types of data.
The statements, opinions and data contained in the journal are solely those of the individual authors and contributors and not of the publisher and the editor(s). We stay neutral with regard to jurisdictional claims in published maps and institutional affiliations.