BEGIN:VCALENDAR
VERSION:2.0
PRODID:-//pretalx//eindhoven2024.pydata.org//cfp//D7YTNK
BEGIN:VTIMEZONE
TZID:Europe/Amsterdam
BEGIN:STANDARD
DTSTART:20001029T030000
RRULE:FREQ=YEARLY;BYDAY=-1SU;BYMONTH=10
TZNAME:CET
TZOFFSETFROM:+0200
TZOFFSETTO:+0100
END:STANDARD
BEGIN:DAYLIGHT
DTSTART:20000326T020000
RRULE:FREQ=YEARLY;BYDAY=-1SU;BYMONTH=3
TZNAME:CEST
TZOFFSETFROM:+0100
TZOFFSETTO:+0200
END:DAYLIGHT
END:VTIMEZONE
BEGIN:VEVENT
UID:pretalx-cfp-WP7S3A@eindhoven2024.pydata.org
DTSTART;TZID=Europe/Amsterdam:20240711T160500
DTEND;TZID=Europe/Amsterdam:20240711T163500
DESCRIPTION:People have been using machine learning for sports betting for 
 decades. Logistic regression applied to horse racing made someone a multi-
 millionaire in the 80s. While fun\, betting is a losing proposition for mo
 st. The house always wins\, right?\n\nWith a friend\, I thought we could b
 eat the house in e-sports by leveraging modern ML tools like LightGBM. E-s
 ports betting is less sophisticated than football or horse racing i.e. the
  market is less efficient. There is a lot of online data and unknown teams
 . It was a space ripe for money-making\, or so we thought.\n\nFirst\, I wi
 ll explain the theory behind e-sports betting with ML: what is an edge\, f
 inancial decision-making\, the expected value and decision rule for one be
 t\, multiple bets with the Kelly criterion\, probability calibration and t
 he winner's curse.\n\nThen\, I will explain how we built a web scraper to 
 extract features\, developed a probabilistic classifier using LightGBM\, d
 efined betting rules using the Kelly criterion\, backtested it with a posi
 tive ROI\, and then lost actual money\, with many priceless lessons coming
  out of it.
DTSTAMP:20250709T215748Z
LOCATION:If (1.1)
SUMMARY:How I lost 1000€ betting on CS:GO with machine learning and Pytho
 n - Pedro Tabacof
URL:https://eindhoven2024.pydata.org/cfp/talk/WP7S3A/
END:VEVENT
END:VCALENDAR