BEGIN:VCALENDAR
VERSION:2.0
PRODID:-//pretalx//pretalx.com//euroscipy-2025//speaker//NEUMLP
BEGIN:VTIMEZONE
TZID:Europe/Warsaw
BEGIN:DAYLIGHT
DTSTART:20240819T000000
TZNAME:CEST
TZOFFSETFROM:+0200
TZOFFSETTO:+0200
END:DAYLIGHT
BEGIN:STANDARD
DTSTART:20241027T030000
RDATE:20251026T030000
TZNAME:CET
TZOFFSETFROM:+0200
TZOFFSETTO:+0100
END:STANDARD
BEGIN:DAYLIGHT
DTSTART:20250330T030000
RDATE:20260329T030000
TZNAME:CEST
TZOFFSETFROM:+0100
TZOFFSETTO:+0200
END:DAYLIGHT
END:VTIMEZONE
BEGIN:VEVENT
SUMMARY:Predictive modeling for imbalanced classification using scikit-lea
 rn - Guillaume Lemaitre\, Olivier Grisel
DTSTART;TZID=Europe/Warsaw:20250819T083000
DTEND;TZID=Europe/Warsaw:20250819T100000
DTSTAMP:20260906T113806Z
UID:pretalx-euroscipy-2025-ASR3XL@pretalx.com
DESCRIPTION:Real-world applications use machine learning to aid decision-m
 aking and planning. Data scientists employ probabilistic models to connect
  input data with outcome predictions that guide operational decisions. A c
 ommon challenge is working with "imbalanced" datasets\, where the outcome 
 of interest occurs rarely compared to total observations. Examples include
  disease detection in medical screening\, fraud identification in transact
 ions\, and discovery of rare physical phenomena like the Higgs boson.\n\nT
 his tutorial examines methodological considerations for handling imbalance
 d datasets. We focus on resampling techniques that adjust the ratio betwee
 n positive and negative outcomes. The tutorial explores: (i) how imbalance
 d data affects probability outcomes and classifier calibration\; (ii) resa
 mpling's impact on model overfitting/underfitting and its connection to re
 gularization\; and (iii) the tradeoffs between computational and statistic
 al performance when implementing resampling strategies.\n\nHands-on progra
 mmatic notebooks provide practical insights into these concepts.\n\nThe ma
 terial and instructions to follow the tutorial will be available here:\nht
 tps://github.com/probabl-ai/calibration-cost-sensitive-learning
LOCATION:Room 1.38 (Ground Floor)
URL:https://pretalx.com/euroscipy-2025/talk/ASR3XL/
END:VEVENT
END:VCALENDAR