2025-11-05 –, AI
A wise man once told me, “It is not only the what that matters - but the WHY.” In today’s rapidly evolving landscape of fraud, relying on opaque machine learning models is no longer feasible. This talk will explore how we can—and should—harness eXplainable AI (XAI) to demystify these “black-boxed” models, providing transparency and valuable insights into the decision-making processes behind fraud detection.
We will discuss how, at PayPal, we leveraged GenAI to personalize model explanations for each business need and overcame significant production scalability challenges while scaling for over 1 Billion accounts. By changing our perspective, we found solutions rooted in a fundamental computer science principle that unlocked new efficiencies and transparency.
As fraud detection becomes increasingly sophisticated, understanding why a machine learning model makes its decisions is paramount. In this session, we’ll explore how eXplainable AI (XAI) can provide transparency and valuable insights into the decision-making processes behind fraud detection algorithms. By shedding light on user behavior patterns, XAI enables more effective fraud detection, fostering trust and accountability while enhancing the overall value of each prediction.
Drawing from our experience at PayPal, we’ll discuss how we leveraged XAI to personalize model explanations, catering to diverse business needs while scaling for over a billion accounts. We’ll demonstrate how overcoming production scalability challenges required a fundamental shift in perspective, which led to more efficient and transparent solutions. Attendees will gain insights into how XAI can be effectively integrated into real-world applications, unlocking new levels of transparency and operational excellence in data-driven decision-making.
No previous knowledge expected
Gal Benor is a Machine Learning Scientist at PayPal. In her day-to-day projects she focuses on developing transparent fraud detection models that safeguard users. She is passionate about eXplainable AI (XAI) and works to make machine learning more interpretable and tailored to specific needs. Gal earned a BSc in Computer Science from Ben-Gurion University and an MSc in Applied Mathematics and Systems Biology from the Weizmann Institute of Science, where she focused her research on breast cancer—an area where transparency is critical, and black-box models are not an option.