In financial services, the competition for customer share is intense with corporations searching for any marketing advantage while countering fraud, money laundering and other challenges. Increased customer satisfaction and loyalty, reduced fraud, and reduced regulatory fines benefit businesses that make successful use of AI. For a variety of situations, including fraud detection and credit risk scoring companies use AI.
For the financial services industry, money laundering is an enormous problem. Every year, an approximate $2 trillion is “cleaned” via the financial system, according to the United Nations Office on Drugs and Crime. Over the last decade, fines for banks that fail to stop money laundering have risen by 500X to more than $10 trillion a year. As a consequence, banks have built up vast teams of individuals and assigned them the time-consuming challenge of detecting and investigating irregular transactions that often take the form of multiple small transfers across a complex network of players. To locate suspicious activity, investigation groups have used rules-based systems. However, the rules easily become redundant and create vast numbers of false positives that are yet to be checked.
AI, especially the modeling of time series, is specifically good at analyzing series of complex transactions and identifying anomalies. Anti-money laundering can detect fraudulent behavior and chains of transactions using machine learning methods. These transactions are flagged for research and can be rated as high, medium or low importance such that their efforts can be prioritized by the investigator. For the decision to mark the transaction, the AI may also include purpose codes. The reason code tells the researcher where they can look to discover the problems and help optimize the investigation process. As they analyze and clarify suspicious transactions, AI may also study from the investigators and instantly strengthen the understanding of the AI model to eliminate trends that do not add to laundered cash.
At Cyber Chasse Inc., the goal is to democratize AI for everyone so that more individuals across sectors can use AI’s power to solve business and social problems. With strong alliances with leading brands, the financial services market is a key focus for the company.
Cyber Chasse enables teams in data science to scale by significantly increasing the pace of building highly precise predictive models. Innovative features of special interest to financial services are integrated including machine learning interpretability, reason codes for individual predictions, automatic modeling of time series etc.