Financial Crime World

Danske Bank Unveils Advanced Machine Learning Fraud Detection Tool

A Collaborative Effort with Teradata’s Think Big Analytics

October 23, 2017 - Anaheim, California

Danske Bank, a leading financial services institution in Denmark, has joined forces with Teradata’s Think Big Analytics arm to develop an AI-driven fraud detection platform that leverages machine learning to analyze tens of thousands of latent features and score millions of online banking transactions in real-time. This cutting-edge tool is expected to achieve 100% ROI in its first year of production.

The Advanced Analytics Engine

The advanced analytics engine, developed by Danske Bank’s Advanced Analytics team in collaboration with Think Big Analytics, has significantly reduced the cost of investigating false positives, increasing overall efficiency and resulting in substantial savings for the bank. This platform uses machine learning to analyze data and identify potential fraudulent transactions, reducing the need for manual review and decreasing the likelihood of human error.

Key Benefits

  • Reduces false positives by 50%
  • Increases fraud detection rates by around 60%
  • Scores incoming transactions in less than 300 milliseconds, providing real-time insight and actionable information
  • Expected to achieve 100% ROI in its first year of production

Addressing the Growing Threat of Fraud

“We recognize that fraud is set to get worse in the near and long-term future due to increased digitization of banking and the prevalence of mobile banking applications,” said Nadeem Gulzar, Head of Advanced Analytics at Danske Bank. “Using AI, we’ve already reduced false positives by 50% and have been able to reallocate half our fraud detection unit to higher-value responsibilities.”

A Scalable Solution for Banks

“We believe that all banks need a scalable, advanced analytics platform as well as a roadmap and strategy for digitalization to bring data science into the organization,” said Mads Ingwar, Client Services Director at Think Big Analytics. “Our AI-driven fraud platform is designed to be flexible and adaptable, allowing it to be easily integrated with existing systems and processes.”

Presenting at Teradata PARTNERS Conference

Danske Bank will share details about its AI-powered engine for fighting financial fraud at the Teradata PARTNERS Conference in Anaheim, California on October 23. The conference brings together industry experts and thought leaders to discuss the latest trends and innovations in data analytics.

Conclusion

The development of this advanced machine learning-based fraud detection tool highlights Danske Bank’s commitment to staying ahead of emerging threats and maintaining its position as one of the most trusted banks in the Nordics. By leveraging AI and machine learning, the bank is able to improve the accuracy and efficiency of its fraud detection process, ultimately protecting its customers’ financial information and assets.