Rules, Machine Learning, and the Best Way to Fight Fraud

For many years, rules-based systems were the preferred method of fraud fighting, but as fraudsters have become more sophisticated, an increasing number of businesses have turned to machine learning. This webinar will walk through the differences between rules and machine learning systems and discuss the pros and cons of both with insights from Paul Curwen, Risk Director at Omise.

Watch Now

In this webinar, you’ll learn:

  • The pros and cons of rules and machine learning systems for fraud prevention
  • The benefits of switching from a rules to a machine learning system
  • How to seamlessly switch to machine learning – even if you have a long-standing rules system in place
  • How Omise’s chargeback rate has significantly decreased since implementing Sift Science
  • How Omise’s full-time fraud team has decreased from four people to one

Watch Now

Kevin Lee

Trust and Safety Architect, Sift Science

Kevin Lee is driven by building high performing teams and systems to combat malicious behavior. He has worked for the last 10+ years around developing strategies, tools and teams responsible for billions of users and dollars of revenue. Prior to Sift Science, Kevin worked as a manager at Facebook, Square and Google where he lead various risk, chargeback, spam and trust and safety organizations.

Paul Curwen

Director of Risk, Omise

Paul Curwen is the Director of Risk at Omise, a leading payment gateway solution in Asia. He has held Risk Management roles at multiple fin-tech companies in Asia and Europe.

Thousands of sites and apps build trust with Sift

Open Table reduced manual review by 80%. 200% improvement in detection accuracy.
60–70% reduction in spam content, more frictionless environments for valued users.
Entropay increased user conversion rates by 15% and now dedicates 0 full-time employees to fraud.