Using Big Data Analytics for Money Laundering Detection – A Case Study

Money laundering is the process that criminals conceal or disguise their crimes and redirect those proceeds into goods or services. Examples of illegal sources of income are betting operations, drug trafficking, illegal gambling and bribery. In this paper, we applied the big data analytics for a case company to detect possible money laundering activities. A partial database from an excel data file with 18,000 transactions along with brief summary report were analyzed beginning with data cleaning, traditional statistics analysis, and data mining process. Autocorrelation functions and partial autocorrelation functions were also conducted to analyze the relationships of attributes in the data set before performing the big data analytics methods. Finally, several time series forecasting methods, including regression methods, exponential smoothing methods, and predictive analytics were used to provide big data approaches and generate reports for decision makers as detection of money laundering activities. Computational results were implemented by using the Minitab and R software.