in fraud detection machine learning is a collection of artificial intelligence algorithms trained with historical data to suggest risk rules you can then implement the rules to block or allow certain user actions such as suspicious logins identity theft or fraudulent transactions ai is designed to create machines that simulate human thinking machine learning is a subset of ai that allows machines to learn from data without being reprogrammed because machines have a much easier job processing a large data set what you get is the ability to slice and dice huge amounts of information this means faster and more efficient detection the system gets to quickly identify suspicious patterns and behaviors that might have taken a human months to find this also means reduced manual review time you'll also get better predictions with larger data sets the more data you feed a machine learning engine the more trained it becomes what's a challenge for human review is a benefit for an ai driven system it's a more cost effective solution unlike hiring more risk ops agents you only need one machine learning system to go through all the data you throw at it regardless of the volume last but not least algorithms don't tire like a human brain fraud managers might not be the most effective at monitoring transactions at 2am after their fifth coffee according to a whitepaper by computer scientists from the university of jakarta machine learning algorithms achieved up to 96 percent accuracy in reducing fraud for e-commerce businesses xi'an see it all [Music] you