Techjockey News

Computer scientists have unveiled a groundbreaking software designed to revolutionize the fight against money laundering. This new tool can swiftly and accurately detect illicit financial activities, capable of scanning a whopping 50 million transactions in one second.

The innovation comes from researchers at the Department of Informatics, who have developed a unique approach to money laundering detection. It relies on advanced algorithms that can rapidly spot instances of criminals splitting large sums into smaller transactions across multiple bank accounts- a tactic called “smurfing.”

These algorithms analyze data from various bank accounts and then focus on the part of the graph exhibiting the most suspicious activity. For instance, if a million pounds are deposited, the software meticulously tracks every related transaction, even if the money is divided among different accounts and expenditures.

Traditional money laundering detection methods rely on rule-based or machine-learning systems, often triggered by predefined suspicious transaction scenarios. These methods can be sluggish and less effective, particularly against smurfing techniques. They also require historical data for accuracy, limiting their usefulness in combating evolving money laundering methods.

Dr. Chen, a Ph.D. student at the Department of Informatics, emphasized the importance of this development in addressing the global money laundering challenge, which constitutes an estimated 2% to 5% of the global GDP, amounting to £632 billion to over £1.5 trillion annually, according to the UNODC.

Dr. Loukides, one of the researchers, stated that their software is 3.2 times more effective at detecting smurfing attacks than existing methods. It’s also highly automated and offers rapid data analysis, making it a powerful tool for money laundering experts.

The software is open-source and freely accessible, making it accessible for financial institutions to combat money laundering more effectively. It has been tested successfully with real data from a Czech bank and fictional cases based on common money laundering patterns.