Institutional Repository of Vilnius University
Dirbtinio Intelekto taikymas nustatant apgaules finansinėse ataskaitose /
Abstract
dc:descriptionEnsuring the reliability of the financial statements and detecting fraud is a critical aspect of an audit. This is usually done using traditional methods such as internal control and analysis of financial information, which, although still widely used for their reliability and understandability, are sometimes ineffective due to their reaction time and cost. A recent solution that can significantly improve the accuracy of financial statements and reduce fraud is the use of artificial intelligence (AI) technologies. IoT techniques, including machine learning and data analytics, can efficiently analyze huge amounts of data, identify anomalies, and uncover subtle signs of fraud that may go undetected using traditional methods. In addition, IoT can automate many audit processes, increasing operational efficiency and allowing auditors to focus on more complex analyses. However, despite these advantages of IoT, integrating these technologies into the financial sector faces challenges related to data confidentiality. Therefore, it is relevant to assess these innovative new technologies and identify their positive and negative aspects, which may have a significant impact in the future. The study aims to assess the methods used to detect fraud in financial statements, compare traditional and modern techniques, and identify the potential of applying artificial intelligence to detect and prevent fraud in financial statements. The main objectives of the work were to analyze the definitions and types of fraud in financial statements, to evaluate different models for detecting fraud, to investigate the possibilities of applying artificial intelligence in fraud detection, to assess auditors' attitudes towards IoT technologies, and to explore the possibilities of integrating artificial intelligence into everyday practice. What was the study's methodology (lit. analysis and empirical study, in summary) The study involved a literature analysis and an empirical study involving surveys and data analysis using software such as SPSS, Stata, or R and Microsoft Excel for data visualization. What are the main findings and recommendations of the study (1-2) 1. Although the literature highlights the effectiveness of AI in detecting financial fraud, the study showed that auditors recognize the potential of AI but do not yet fully trust and use it due to existing data confidentiality gaps. 2. There is a need to continuously improve the ethics and transparency of these systems by implementing strong data privacy and security controls to ensure client confidentiality and avoid algorithmic bias.
Degree
thesis:*- Grantor dc:publisher
- Institutional Repository of Vilnius University
- Year dc:date
- 2024
Author and committee
dc:creator, dc:contributor.*- Author dc:creator
-
- Masalskis, Gabrielius,
Rights
dc:rights- Statement dc:rights
-
- info:eu-repo/semantics/openAccess
- Language dc:language
- lit
Identifiers
dc:identifier.*- Repository record dc:identifier
- https://repository.vu.lt/VU:ELABAETD210638555&prefLang=en_US