Money laundering (ML) is an illegal campaign to dissemble black money into clean money. Nowadays, the world banking system identification of money laundering has become a difficult task due to the large volume of banking transactions that eventually affect the global economy. ML fraud is a million-dollar business and rising every year. On the other side, Anti money laundering (AML) is the system that fights against money laundering. There are no useful AML methods which are available to prevent this unethical crime. However, financial action task force (FATF) is a global organization, which is working against financial crime like money laundering, credit card fraud. It was started in 1989 to fight against money laundering. Data mining methods have been widely used by many researchers to handle money laundering. This study contains detail review of various data mining methods like k-means clustering, hierarchical clustering, KNN, regression analysis, XGBoost and hybrid models used for detection and prediction of money laundering. We have also discussed the limitations of previous work and suggestion for the future research. Keywords: Money laundering, suspicious transaction, AML, Supervised learning methods, unsupervised learning methods.
• Hardware: Processor: i3 ,i5 RAM: 4GB Hard disk: 16 GB • Software: operating System : Windws2000/XP/7/8/10 Anaconda,jupyter,spyder,flask Frontend :-python Backend:- MYSQL
₹10000 (INR)
NON IEEE -2021