BEGIN:VCALENDAR
VERSION:2.0
PRODID:-//pretalx//talks.python-summit.ch//swiss-python-summit-2026//speak
 er//JULC8X
BEGIN:VTIMEZONE
TZID:Europe/Zurich
BEGIN:DAYLIGHT
DTSTART:20251023T000000
TZNAME:CEST
TZOFFSETFROM:+0200
TZOFFSETTO:+0200
END:DAYLIGHT
BEGIN:STANDARD
DTSTART:20251026T030000
RDATE:20261025T030000
TZNAME:CET
TZOFFSETFROM:+0200
TZOFFSETTO:+0100
END:STANDARD
BEGIN:DAYLIGHT
DTSTART:20260329T030000
RDATE:20270328T030000
TZNAME:CEST
TZOFFSETFROM:+0100
TZOFFSETTO:+0200
END:DAYLIGHT
END:VTIMEZONE
BEGIN:VEVENT
SUMMARY:Did we break up? Auditing Instagram data with Python - Almudena Ba
 rreiro Carrillo
DTSTART;TZID=Europe/Zurich:20261023T154000
DTEND;TZID=Europe/Zurich:20261023T161000
DTSTAMP:20261111T040115Z
UID:pretalx-swiss-python-summit-2026-UT3EWL@talks.python-summit.ch
DESCRIPTION:Instagram logs every interaction: likes\, messages\, stories v
 iewed\, searches\, and follower changes. Even if you post nothing\, your a
 ctivity leaves a digital footprint.\n\nIn this talk\, we will explore how 
 to access and analyze the personal data Instagram collects about you. We w
 ill use Python\, with libraries like pandas or polars\, to clean and struc
 ture the information downloaded directly from the platform's privacy porta
 l.\n\nNext\, we will build an interactive dashboard using Dash to visualiz
 e behavioral patterns over time. We will apply time-series anomaly detecti
 on techniques (such as rolling z-score\, IsolationForest\, or DBSCAN) and 
 supervised classifiers (RandomForestClassifier\, LogisticRegression) to id
 entify potentially significant shifts in your digital activity—like a br
 eakup.\n\nFinally\, we will reflect on the economic value of this data\, t
 he inferences platforms can make about our personal lives\, and briefly di
 scuss the European AI Act's relevance to privacy protection.
LOCATION:Aula 4.101
URL:https://talks.python-summit.ch/swiss-python-summit-2026/talk/UT3EWL/
END:VEVENT
END:VCALENDAR