BEGIN:VCALENDAR
VERSION:2.0
PRODID:-//Date iCal//NONSGML kigkonsult.se iCalcreator 2.20.2//
METHOD:PUBLISH
X-WR-CALNAME;VALUE=TEXT:Eventi DIAG
BEGIN:VTIMEZONE
TZID:Europe/Paris
BEGIN:STANDARD
DTSTART:20211031T030000
TZOFFSETFROM:+0200
TZOFFSETTO:+0100
RDATE:20221030T030000
TZNAME:CET
END:STANDARD
BEGIN:DAYLIGHT
DTSTART:20220327T020000
TZOFFSETFROM:+0100
TZOFFSETTO:+0200
TZNAME:CEST
END:DAYLIGHT
END:VTIMEZONE
BEGIN:VEVENT
UID:calendar.24883.field_data.0@www.u-gov-ricerca.uniroma1.it
DTSTAMP:20260406T010645Z
CREATED:20220502T154320Z
DESCRIPTION:La Prof.ssa Dolores Romero Morales è visiting Professor presso 
 il DIAG dal 1 al 31 maggio 2022.Where: Aula Magna DIAG & online su piattaf
 orma Meet  When: May 6\, 2022 - 15:00AbstractThere is a pressing need to m
 ake Data Science tools more transparent. Despite excellent accuracy\, stat
 e-of-the-art Data Science models effectively work as black boxes\, which h
 inders model validation and may hide unfair outcomes for risk groups. Tran
 sparency is of particular importance for high stakes decisions\, is requir
 ed by regulators for models aiding\, for instance\, credit scoring\, and s
 ince 2018 the EU has extended this requirement by imposing the so-called r
 ight-to-explanation in algorithmic decision-making. From the Mathematical 
 Optimization perspective\, this means that we need to strike a balance bet
 ween several objectives\, namely accuracy\, transparency\, and fairness. I
 n this presentation\, we will navigate through some novel techniques that 
 embed explainability and fairness in the construction of Data Science mode
 ls. This includes the ability to provide global\, local and counterfactual
  explanations\, as well as model cost-sensitivity and fairness requirement
 s.  We will show the versatility of our methodology when applied to more c
 omplex data types such as functional data.
DTSTART;TZID=Europe/Paris:20220506T153000
DTEND;TZID=Europe/Paris:20220506T153000
LAST-MODIFIED:20220505T085026Z
LOCATION:Aula Magna
SUMMARY:The role of Mathematical Optimization to enhance Transparency in Da
 ta Science - \n    \n                  \n    Dolores Romero Morales\n\nent
 e provenienza: \n\nBusiness School Copenaghen\n\nperiodo visita: \n\nMay\,
  2022 to June\, 2022\n\ngruppo di ricerca: \n\nContinuous Optimization\n\n
 keywords ricerca: \n\nBig Data Optimization\n\ninvitato da: \n\npalagi@dis
 .uniroma1.it\n\nCognome visiting: \n\nRomero Morales\n\nNome visiting: \n
 \nDolores
URL;TYPE=URI:http://www.u-gov-ricerca.uniroma1.it/node/24883
END:VEVENT
END:VCALENDAR