BEGIN:VCALENDAR
VERSION:2.0
PRODID:-//pretalx//pretalx.com//pyconde-pydata-2026//talk//MLUK9M
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-2026-MLUK9M@pretalx.com
DTSTART;TZID=CET:20260416T154500
DTEND;TZID=CET:20260416T161500
DESCRIPTION:Why did the model say "No"? In an era where machine learning mo
 dels increasingly influence high-stake decisions\, "trust me" isn't a suff
 icient explanation. Yet\, the logic behind many model decisions remains a 
 black box\, often hiding bias and making it difficult to establish trust.\
 n\nIn this talk\, we move beyond the mystery of the "ghost in the machine"
  and into practical debugging using a structured *XAI Decision Tree*. Inst
 ead of guessing which method to use\, we will walk through a logical frame
 work that narrows down the field based on a few critical questions: the ty
 pe of data you have\, the level of model access available\, and whether yo
 u need to explain a single prediction or the entire system.\n\nThe audienc
 e will leave with a clear path to choosing the right explainable AI (XAI) 
 method - such as SHAP\, LIME\, or Integrated Gradients - and the correspon
 ding Python framework for their specific use case.\n\nThis session will co
 ver:\n\n- Importance of XAI: Understanding why XAI is crucial using a real
 -world example\n- XAI Landscape: An overview of existing XAI methods and h
 ow they are related\n- XAI Decision Tree: How to use the structured XAI de
 cision tree to choose the right explanation method for your use case\n- Lo
 cal vs global: A common understanding of local vs global explainability\n-
  XAI in Practice: XAI in practice as well as corresponding Python framewor
 ks to use
DTSTAMP:20260523T181833Z
LOCATION:Titanium [2nd Floor]
SUMMARY:Why Did The Model Do That? Debugging the Ghost in the Machine - Cos
 ima Meyer
URL:https://pretalx.com/pyconde-pydata-2026/talk/MLUK9M/
END:VEVENT
END:VCALENDAR
