BEGIN:VCALENDAR
VERSION:2.0
PRODID:-//pretalx//pretalx.com//pyconde-pydata-berlin-2023//talk//CHLT3D
BEGIN:VTIMEZONE
TZID:CET
BEGIN:STANDARD
DTSTART:20001029T040000
RRULE:FREQ=YEARLY;BYDAY=-1SU;BYMONTH=10
TZNAME:CET
TZOFFSETFROM:+0200
TZOFFSETTO:+0100
END:STANDARD
BEGIN:DAYLIGHT
DTSTART:20000326T030000
RRULE:FREQ=YEARLY;BYDAY=-1SU;BYMONTH=3
TZNAME:CEST
TZOFFSETFROM:+0100
TZOFFSETTO:+0200
END:DAYLIGHT
END:VTIMEZONE
BEGIN:VEVENT
UID:pretalx-pyconde-pydata-berlin-2023-CHLT3D@pretalx.com
DTSTART;TZID=CET:20230417T151000
DTEND;TZID=CET:20230417T154000
DESCRIPTION:Proper monitoring of machine learning models in production is e
 ssential to avoid performance issues. Setting up monitoring can be easy fo
 r a single model\, but it often becomes challenging at scale or when you f
 ace alert fatigue based on many metrics and dashboards. \n\nIn this talk\,
  I will introduce the concept of test-based ML monitoring. I will explore 
 how to prioritize metrics based on risks and model use cases\, integrate c
 hecks in the prediction pipeline and standardize them across similar model
 s and model lifecycle. I will also take an in-depth look at batch model mo
 nitoring architecture and the use of open-source tools for setup and analy
 sis.
DTSTAMP:20260421T234339Z
LOCATION:A1
SUMMARY:Staying Alert: How to Implement Continuous Testing for Machine Lear
 ning Models - Emeli Dral
URL:https://pretalx.com/pyconde-pydata-berlin-2023/talk/CHLT3D/
END:VEVENT
END:VCALENDAR