This thesis explores the application of machine learning techniques for the detection of money laundering activities, a persistent challenge in the financial sector that undermines the integrity of economic systems worldwide. The study begins with a comprehensive introduction to money laundering, outlining its processes, the difficulties in traditional detection methods, and the significant potential of machine learning as a transformative approach. A thorough literature review reveals the landscape of existing research on money laundering detection, highlighting the limitations of conventional methods and the emergence of data-driven strategies. Key machine learning algorithms, including supervised and unsupervised learning techniques, are examined for their applicability to fraud detection, providing a theoretical framework for subsequent analysis.