Webinar Banner


Despite spending $1 billion on fraud detection software each year, fraudulent activity still costs banks over $50 billion annually in a rising trend that doesn't appear likely to change!

Sophisticated financial criminals are constantly changing their tactics. AI-based detection systems, dependent on large training sets of historical data, may be good at catching the low-value frauds but may struggle to pick up on the newest highest-risk approaches.

In this webinar, Harry Powell, Head of Global Solutions at TigerGraph and ex Barclays, will talk about leveraging graph-based features to overcome the accuracy barrier in fraud detection machine learning.

Machine Learning has transformed fraud detection in the last ten years, but it has hit a limit. Tuning your ML algorithms with traditional approaches has reached the point of diminishing yield returns. To deliver the next level of performance some fraud teams have introduced a new type of input data feature which carries extra information about fraudulent activity: contextual graph features based on the network of relationships in your data.

This talk will explore how graph databases can easily and quickly augment your existing AI-based detection systems and give you tools for intelligent investigation, transforming your ability to respond to fraud and sending a strong message to organized criminals to leave your bank alone.

Here's what you'll learn:

What are the limitations of Machine Learning and their effects on fraud detection solutions?

How to reach the next level of fraud detection performance by using contextual graph features.

The results achieved by 4 of the Tier 1 US banks

Your presenters:

Ronald Prätsch

Ronald Prätsch
Fraud Consultant, Co-Founder

Ronald leverages his extensive experience in payments & fraud to inform the structure and content of the site. Outside of About-Fraud, Ronald consults regularly with merchants, payment service providers and fraud solution vendors. Before About-Fraud, he spent close to a decade in various payments and fraud prevention roles at Sift Science, Fareportal, Booking.com and Pay on.


Harry Powell
Head of Industry Solutions

In one of his previous roles, Harry was the Director of Advanced Analytics at Barclays, which released a number of world-class data science innovations to production, including the first Apache Spark application in the European financial services industry. Harry has been working with graph data on and off for 10 years, and while at Barclays his team built a number of graph applications.