Fighting financial fraud at Danske Bank with artificial intelligence

Fraud in banking is an arms race with criminals using machine learning to improve their attack effectiveness. Ron Bodkin and Nadeem Gulzar explore how Danske Bank uses deep learning for better fraud detection, covering model effectiveness, TensorFlow versus boosted decision trees, operational considerations in training and deploying models, and lessons learned along the way.

Danske Bank, the leader in mobile payments in Denmark, is innovating with AI. Danske Bank’s existing fraud detection engine is being enhanced with deep learning algorithms that can analyze potentially tens of thousands of latent features. Danske Bank’s current system is largely based on handcrafted rules created by the business, based on intuition and some light analysis. The system is effective at blocking fraud, but it has a high rate of false positives, which is expensive and inconvenient, and it has proved impractical to update and maintain as fraudsters evolve their capabilities. Moreover, the bank understands that fraud is getting worse in the near- and long-term future due to the increased digitization of banking and the prevalence of mobile banking applications and recognizes the need to use cutting-edge techniques to engage fraudsters not where they are today but where they will be tomorrow. Application fraud is an important emerging trend, in which machines fill in transaction forms. There is evidence that criminals are employing sophisticated machine-learning techniques to attack, so it’s critical to use sophisticated machine learning to catch fraud in banking and mobile payment transactions. Ron Bodkin and Nadeem Gulzar explore how Danske Bank uses deep learning for better fraud detection. Danske Bank’s multistep program first productionizes “classic” machine learning techniques (boosted decision trees) while in parallel developing deep learning models with TensorFlow as a “challenger” to test. The system was first tested in shadow production and then in full production in a champion-challenger setup against live transactions. Ron and Nadeem explain how the bank is integrating the models with the efforts already running, giving the bank and its investigation team the ability to adapt to new patterns faster than before and taking on complex highly varying functions not present in the training examples.