BEGIN:VCALENDAR
VERSION:2.0
PRODID:-//pretalx//pretalx.com//euroscipy-2026//speaker//DDHUTN
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-euroscipy-2026-FL89YS@pretalx.com
DTSTART;TZID=CET:20260722T140000
DTEND;TZID=CET:20260722T153000
DESCRIPTION:Machine Learning practitioners often face a trade-off: high acc
 uracy with complex\, black-box models (like XGBoost or Random Forests) or 
 lower accuracy with transparent models (like decision trees or linear mode
 ls). **What if you didn't have to choose?**\nThis 90-minute tutorial intro
 duces **TRUST** (**T**ransparent\, **R**obust\, and **U**ltra-**S**parse *
 *T**rees)\, a new interpretable regression framework that combines decisio
 n trees with sparse linear models to deliver Random Forest accuracy. The a
 lgorithm is implemented in the Python package `trust-free` (available via 
 pip install). We will demonstrate how TRUST autonomously recovers the WHO 
 obesity threshold (BMI = 30) from raw data to inform medical risk pricing.
 \nBy the end\, you will be able to train high-performing\, interpretable r
 egression models and generate automated\, natural-language explanation rep
 orts for individual predictions and deterministic feature importance.
DTSTAMP:20260603T190232Z
LOCATION:Room 1.19 (Ground Floor\, Shannon)
SUMMARY:From Black to White Boxes: Interpretable Regression with the trust-
 free Python package - Albert Dorador
URL:https://pretalx.com/euroscipy-2026/talk/FL89YS/
END:VEVENT
END:VCALENDAR