Train, Evaluate, Repeat: Building a Credit Card Fraud Detection System - Leela Senthil Nathan

PyData LA 2018
This talk covers three major ML problems Stripe faced (and solved!) in building its credit card fraud detection system: choosing labels for fraud that work across all merchants, addressing class imbalance (legitimate charges greatly outnumber fraudulent ones), and performing counterfactual evaluation (to measure performance and obtain training data when the ML system is changing outcomes itself).
---
www.pydata.org
PyData is an educational program of NumFOCUS, a 501(c)3 non-profit 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 global PyData network promotes discussion of best practices, new approaches, and emerging technologies for data management, processing, analytics, and visualization. PyData communities approach data science using many languages, including (but not limited to) Python, Julia, and R.
PyData conferences aim to be accessible and community-driven, with novice to advanced level presentations. PyData tutorials and talks bring attendees the latest project features along with cutting-edge use cases. 00:00 Welcome!
00:10 Help us add time stamps or captions to this video! See the description for details.
Want to help add timestamps to our KZbin videos to help with discoverability? Find out more here: github.com/numfocus/KZbinVi...

[@lebronx9516]

Great presentation!

[@weitao9926]

great session! thanks for sharing!

[@alibagheri411]

great talk

[@lililhama1831]

Loved this class! I have one question: on que learning part, what does it mean to have a constant target rate instead of fixed subsampling rate? I thought those rates were complementary like x% and 1-x%. What did I miss?