Presented By O'Reilly and Cloudera
Make Data Work
September 25–26, 2017: Training
September 26–28, 2017: Tutorials & Conference
New York, NY

Fighting financial fraud at Danske Bank with artificial intelligence

Nadeem Gulzar (Danske Bank Group), Sune Askjær (Think Big Analytics, a Teradata Company)
4:35pm5:15pm Wednesday, September 27, 2017
Artificial Intelligence, Machine Learning & Data Science
Location: 1A 12/14 Level: Intermediate
Secondary topics:  Financial services, Platform
Average rating: *****
(5.00, 3 ratings)

Who is this presentation for?

  • CFOs, CIOs, CTOs, enterprise architects, data scientists, and data engineers

Prerequisite knowledge

  • Basic knowledge of financial fraud
  • An understanding of unsupervised machine learning

What you'll learn

  • Explore how Danske Bank uses deep learning for better fraud detection


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.

Sune Askjaer 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. Sune 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.

Photo of Nadeem Gulzar

Nadeem Gulzar

Danske Bank Group

Nadeem Gulzar is the head of advanced analytics and architecture at Danske Bank Group, a Nordic bank with strong roots in Denmark and a focus on becoming the most trusted financial partner in the Nordics. Nadeem has taken the lead in establishing advanced analytics and big data technologies within Danske. Previously, he worked with Credit and Marketrisk, where he headed a program to build-up capabilities to calculate risk using Monte Carlo simulation methods. Nadeem holds a BS in computer science, mathematics, and psychology and a master’s degree in computer science, both from Copenhagen University.

Sune Askjær

Think Big Analytics, a Teradata Company

Acting Director for Data Science for the NordREE region (Norther & Eastern Europe incl. Russia) and currently works out of the Think Big Analytics office in Copenhagen, Denmark.
Sune holds a M.Sc. in Engineering from the Technical University of Denmark and a Ph.D. from the University of Copenhagen and has worked with machine learning and advanced analytics in different R&D organizations for more than 12 years.

Comments on this page are now closed.


Michael Higgins | DATA ANALYST
10/04/2017 9:31am EDT

I loved this talk. Is there a place to get the slides?