Using Data Science To Take The Profit Out Of Crime

Using Data Science To Take The Profit Out Of Crime

Aretec Employs Proven Software Development Quality Management Processes to Develop Production-Ready Data Science Solutions


Money laundering is the act of concealing the transformation of profits from illegal activities and corruption into ostensibly “legitimate” assets. The dilemma of illicit activities is accounting for the origin of the proceeds of such activities without raising the suspicion of law enforcement agencies. The processes by which criminally derived property may be laundered are extensive. Though criminal money may be successfully laundered without the assistance of the financial sector, the reality is that hundreds of billions of dollars of criminally derived money is laundered through financial institutions, annually. The nature of the services and products offered by the financial services industry means that it is vulnerable to abuse by money launderers. Aretec’s client had a requirement to develop a solution that analyzes large amounts of data provided by financial institutions for violations of Anti-Money Laundering (AML) regulations.


The objective of Aretec’s AML solution is to enforce the fact that it is wrong for individuals and organizations to assist criminals to benefit from the proceeds of their criminal activity or to facilitate the commission of such crimes by providing financial services to them. In accordance with the Bank Secrecy Act and the USA PATRIOT Act frameworks, Aretec developed a solution that analyzes data provided by financial institutions for violations of AML regulations. Our AML solutions allowed users to perform quantitative analyses on registrants to identify potential instances of money laundering. The AML solution collects, normalizes, and uploads large data sets in order to perform detailed analysis into registrant activities. The AML module helps quantitative researchers, financial engineers, and examiners the ability to determine: 1) If there are any possible instances of money laundering; and 2) The effectiveness of registrant AML transaction monitoring and reporting programs.


• An application that takes an organization’s best analytical practices and incorporates them into one tool
• Process-driven, reliable, consistent data transformations and analytics
• Sandbox analytics for custom analytics
• Quick identification of data outliers and anomalies
• Enables examiners to handle more edge cases automatically that would otherwise take significant time and knowledge to sift through
• Becomes a reference source codifying best practices/documentation (e.g., reference manuals, report queries, etc.)