BEGIN:VCALENDAR
VERSION:2.0
PRODID:-//pretalx//pretalx.com//pyconde-pydata-2024//talk//XDQNCR
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-2024-XDQNCR@pretalx.com
DTSTART;TZID=CET:20240422T134500
DTEND;TZID=CET:20240422T143000
DESCRIPTION:Every day\, we engage with news\, and more often\, these are cu
 rated by recommendation engines. Building such an algorithm poses some uni
 que challenges\, different from movie or product recommendations: articles
  have a short lifetime because nothing is older than yesterday's news. The
  data is heavily biased by the different positioning of articles on the pa
 ge\, and journalistic principles and brand identity should be represented 
 in the article selection. At Axel Springer National Media and Tech\, we ov
 ercome these challenges by leveraging our domain knowledge combined with s
 imple statistics instead of black-box machine learning models. This talk w
 ill share some of our learnings that can be applied to recommendation syst
 ems and data science projects in general.
DTSTAMP:20260608T022013Z
LOCATION:A1
SUMMARY:Tailored and Trending: Key learnings from 3 years of news recommend
 ations - Dr. Christian Leschinski
URL:https://pretalx.com/pyconde-pydata-2024/talk/XDQNCR/
END:VEVENT
END:VCALENDAR