Artificial Intelligence in the 2010s was dominated by machine learning, with deep neural networks and reinforcement learning delivering advancements in image captioning, natural language translation, and game playing. But the unstructured, changing nature of fraud was ill-suited to the complexity of machine learning, slowing the advancement of automated fraud detection. During this session, we'll discuss:
Criteria to identify high-ROI AI opportunities including the successes and challenges Kount has seen pursuing them
How next wave AI technologies like network analysis, expert knowledge transfer, and small sample learning may be better suited to the fraud domain than supervised machine learning
Strategies for maturing AI and ML teams and broadening the ability to incorporate these technologies
Request to be notified when this session is made available.
We will notify guest when this session will become available.
Josh Johnston is an artificial intelligence scientist who exploits information, automates decisions, and focuses attention on relevant data. He has led research teams fighting credit card fraud, developing self-driving cars, autonomy for bomb disposal robots, and scientific visualization in virtual reality and augmented reality. Josh received a Bachelor of Science in electrical engineering and mechanical engineering from Duke University and a Master of Science in robotics from Carnegie Mellon University.