This talk covers three major ML problems that Stripe faced (and solved!) when creating its credit card fraud detection system: choosing fraud labels that work for all merchants, addressing the imbalance of class (legitimate charges greatly outnumber fraudulent charges) and perform a counterfactual evaluation (to measure performance and obtain training data when the ML system itself modifies the results).

—

www.pydata.org

PyData is an educational program of NumFOCUS, a 501(c)3 nonprofit organization in the United States. PyData provides a forum for the international community of users and developers of data analysis tools to share ideas and learn from each other. The PyData Global Network promotes discussion of best practices, new approaches and emerging technologies for data management, processing, analysis and visualization. PyData communities approach data science using many languages, including (but not limited to) Python, Julia, and R.

PyData conferences are intended to be accessible and community-focused, with presentations from beginner to advanced level. PyData tutorials and conferences introduce participants to the latest project features as well as cutting-edge use cases. 00:00 Welcome!
00:10 Help us add timestamps or captions to this video! See description for details.

Want to help us add timestamps to our YouTube videos for easier discovery? Learn more here: https://github.com/numfocus/YouTubeVideoTimestamps

Please take the opportunity to connect and share this video with your friends and family if you find it useful.