BEGIN:VCALENDAR
VERSION:2.0
PRODID:-//CFP.DEV//CFP.DEV shortcodes//EN
CALSCALE:GREGORIAN
METHOD:PUBLISH
X-WR-CALNAME:Voxxed Days Zürich 2026
X-WR-RELCALID:c426493a-54d4-472b-b975-6f3aaa7163fa
X-WR-TIMEZONE:Europe/Brussels
BEGIN:VEVENT
UID:cfp-1151-13559@cfp.dev
DTSTAMP:20261005T212956Z
SEQUENCE:0
STATUS:CONFIRMED
DTSTART:20260324T091000Z
DTEND:20260324T095500Z
SUMMARY:From Shadows to Spotlight - How Swiss Post Performs Reliable ML Dep
 loyment
DESCRIPTION:Moving a machine learning model from exploration into productio
 n is never a straight path.Academic success often relies on clean datasets
 \, controlled environments\, and benchmark metrics—but in the real world
 \, models face data drift\, latency constraints\, integration challenges\,
  and the risk of wrong predictions directly impacting customers and busine
 ss processes.In this talk\, we share our journey of bringing fraud detecti
 on models from research into production at Swiss Post. We highlight the ro
 le of the shadow model approach\, where new models run in parallel with pr
 oduction systems to safely validate performance on live traffic.You’ll l
 earn how shadow testing helps measure robustness\, monitor data drift\, an
 d align with business KPIs—without introducing operational risk.Attendee
 s will take away concrete practices for bridging the gap between academic 
 experimentation and real-world operations: how to design safe rollouts\, b
 uild monitoring pipelines\, and decide when a model is ready for prime tim
 e.\nSpeakers: Giovanni Degiorgi\nTrack: Data
URL:https://vdz26.voxxeddays.ch/talk/from-shadows-to-spotlight-how-swiss-po
 st-performs-reliable-ml-deployment/
LOCATION:Room 4\nARENA Cinemas\, Sihlcity\nZürich\, Switzerland
CATEGORIES:Data
END:VEVENT
END:VCALENDAR