BEGIN:VCALENDAR
VERSION:2.0
PRODID:-//pretalx//cfp.pydata.org//pydataglobal2025//speaker//APLPNP
BEGIN:VEVENT
UID:pretalx-pydataglobal2025-J7JK79@cfp.pydata.org
DTSTART:20251210T123000Z
DTEND:20251210T130000Z
DESCRIPTION:Building ML models for financial fraud detection sounds straigh
 tforward\, until you have to evaluate\, validate\, and deploy them in real
 -world pipelines. This talk walks through the practical stack\, metrics\, 
 and mindsets needed to build fraud detection systems with modern Python. W
 e'll cover key challenges like concept drift\, extreme class imbalance\, f
 alse-positive overload\, and why the usual ML workflows fall short. Along 
 the way\, we’ll explore a real-world architecture using classical ML\, d
 eep learning\, and GNNs\, plus the validation techniques and production pa
 tterns that make or break fraud systems. If you're tired of toy problems a
 nd want patterns that survive real money and real latency\, this talk’s 
 for you.
DTSTAMP:20260417T062437Z
LOCATION:Machine Learning & AI
SUMMARY:Realtime Financial Fraud Detection with Modern Python - César Soto
  Valero
URL:https://cfp.pydata.org/pydataglobal2025/talk/J7JK79/
END:VEVENT
BEGIN:VEVENT
UID:pretalx-pydataglobal2025-ZXVYCB@cfp.pydata.org
DTSTART:20251210T140000Z
DTEND:20251210T143000Z
DESCRIPTION:The modern Python ecosystem shortens the distance between idea 
 and implementation. This talk presents a focused workflow to move from a b
 usiness question to a working prototype\, fast. We'll explore reproducible
  environments (uv\, Docker)\, quick data iteration with polars and duckdb\
 , clean project scaffolding (pyproject.toml)\, and lightweight service lay
 ers with FastAPI and pydantic. Along the way\, we’ll integrate tests (py
 test)\, static checks (mypy)\, and fast linting (ruff). You’ll leave wit
 h a reusable structure\, toolchain recommendations\, and a mental model fo
 r optimizing feedback loops and development in modern Python projects.
DTSTAMP:20260417T062437Z
LOCATION:Data Engineering & Infrastructure
SUMMARY:From Ideas to APIs: Delivering Fast with Modern Python - César Sot
 o Valero
URL:https://cfp.pydata.org/pydataglobal2025/talk/ZXVYCB/
END:VEVENT
END:VCALENDAR
