Pemanfaatan Machine Learning untuk Deteksi Kecurangan Laporan Keuangan : Sintesis Literatur
Artificial intelligence advancements are transforming accounting and auditing methods, particularly in identifying fraud in increasingly complicated financial accounts The limitations of conventional audit methods in identifying patterns of anomalies in large-scale data have led to the use of machine learning as a more efficient approach. This study was to investigate global research trends, identify the methods employed, and suggest future research prospects. The method used was a systematic literature review (SLR) based on PRISMA criteria, with 162 publications picked from the Scopus database between 2019 and 2024 The results show a huge rise in research. Decision trees, support vector machines, and neural networks are the most commonly utilized algorithms for categorizing fraud and non-fraud data. Although effective, the method is limited in terms of interpretability and data requirements. This study provides an overview of the current state of the art and lays the groundwork for future technology-based audit research and practice.