Purpose- The purpose of this study is to determine studies on detecting different types financial frauds, financial statement frauds and methods used in these studies. Financial statement fraud is one of the most common types of white-collar crime that has plagued various industries worldwide. It involves manipulating financial information in order to deceive stakeholders, such as investors and regulators, for personal gain or advantages. Financial statement fraud has significant implications for stakeholders, including investors, regulators, and the general public. Detecting fraudulent activities in financial statements is crucial for ensuring transparency, reliability, and trust in financial reporting. Methodology- This paper presents a comprehensive literature review of studies focused on detecting frauds in financial statements in between 2019 and first half of 2023 inclusive on Science Direct. Findings - The review encompasses a range of research articles, providing insights into various methodologies, techniques, and advancements in fraud detection. The findings of this review contribute to the understanding of fraud detection mechanisms in financial statements and inform future research directions in this critical area. Conclusion - This paper presents a comprehensive literature review on the topic of detecting financial statement fraud, focusing on current trends and approaches employed in the field. By examining a wide range of scholarly articles, research studies, and industry reports, this review aims to provide an overview of the existing knowledge, methodologies, and tools utilized in the detection of financial statement fraud. In recent years, it has been observed that studies using machine learning in the field of fraud detection have increased. Keywords: Fraud detection, machine learning, data mining literature review, financial statements JEL Codes: M42, M21, M41