We would like to keep you up to date with the latest news from Digitalisation World by sending you push notifications.
“Application fraud is a critical, top of the agenda issue for banks, and there is evidence that criminals are becoming savvier by the day; employing sophisticated machine learning techniques to attack, so it’s critical to use advanced techniques, such as machine learning to catch them,” said Nadeem Gulzar, Head of Advanced Analytics, Danske Bank. “The bank understands that fraud is set to get worse in the near and long-term future due to the increased digitisation of banking and the prevalence of mobile banking applications. We recognise the need to use cutting-edge techniques to engage fraudsters not where they are today, but where they will be tomorrow. Using AI, we’ve already reduced false positives by 50% and as such have been able to reallocate half the fraud detection unit to higher value responsibilities.”
Danske Bank’s original fraud detection system was largely based on handcrafted rules that had been proactively applied by the business over time. With record numbers of false positives - at times reaching 99.5% of all transactions - the costs and time associated with investigation had become significant, with the bank’s large fraud detection team feeling overworked, yet not effectively utilised.
Teradata’s Think Big Analytics team began working with Danske Bank in autumn 2016, to augment their advanced analytics team with specialist knowledge about how to utilise data to bring greater benefits to the wider business. The joint team began with building a framework within the bank’s existing infrastructure and then created advanced machine learning models to detect fraud within millions of transactions per year, and in peak times, many hundreds of thousands per minute. To ensure transparency and encourage trust, the engine includes an interpretation layer on top of the machine learning models, providing explanations and interpretation of blocking activity.
From a modelling point of view, fraud cases are still very rare, with around one fraud case in every 100,000. The team has managed to take the false positives from the models and reduce them by 50%. At the same time, they are able to catch more fraud - actually upping the detection rate by around 60. Danske Bank’s anti-fraud programme is the first to put machine learning techniques into production while simultaneously developing deep learning models to test the techniques.
“All banks need a scalable, advanced analytics platform, as well as a roadmap and strategy for digitalisation to bring data science into the organisation.” says Mads Ingwar, Client Services Director at Think Big Analytics. “For online transactions, credit cards and mobile payments, banks need a real-time solution - the state of the art AI-driven fraud platform we have developed in collaboration with Danske Bank scores incoming transactions in less than 300 milliseconds. It means that when customers are standing in the supermarket and buying groceries, the system can score the transaction in real-time and provide immediately actionable insight. This type of solution is one we’ll begin to see throughout organisations in the financial services industry,”