Effectiveness and Reliability of Artificial Intelligence in Fraud Detection: A Mixed-Method Study on Financial Audit

Financial statement fraud threatens investor trust at a substantial level in the present market conditions. AI technology, through data pattern analysis, helps financial auditing reach better results when detecting rumors along with anomalies and suspicious trends. This research evaluates artificial intelligence's effectiveness in yeast-free detection systems through several investigative methods. An evaluation of AI systems by professionals indicates their ability to detect financial statement fraud accurately. A quantitative analysis of historical data through AI enables fraud pattern detection according to this study method. The researchers who utilize the qualitative method meet with forensic accountants for their research work. The research delivers both forensic accountants and financial auditors definitive information about the challenges they face and their perspectives toward AI system implementation in audit procedures. The results show that AI is very successful when recognising fraud trends, particularly when using machine learning and deep learning approaches. However, the quality of the data and the settings of the algorithms still have an impact on how reliable AI is. Furthermore, despite ongoing worries about result interpretation and accountability of AI models, qualitative data suggests that auditors generally embrace AI as a tool that speeds up the audit process. According to the study's findings, artificial intelligence (AI) can effectively assist financial audits; however, to improve the validity of fraud detection, it should be used in addition to the analysis of qualified examiners. To increase the accuracy of fraud detection in the future, this study suggests creating more transparent AI models and integrating AI with blockchain technology.