BEGIN:VCALENDAR
VERSION:2.0
PRODID:-//Talks.cam//talks.cam.ac.uk//
X-WR-CALNAME:Talks.cam
BEGIN:VEVENT
SUMMARY:Landscape and Gaps in Open Source Fairness Toolkits - Michelle Lee
DTSTART:20210302T131500Z
DTEND:20210302T141500Z
UID:TALK156034@talks.cam.ac.uk
CONTACT:Mateja Jamnik
DESCRIPTION:"Join us on Zoom":https://zoom.us/j/99166955895?pwd=SzI0M3pMVE
 kvNmw3Q0dqNDVRalZvdz09\n\nWith the surge in literature focusing on the ass
 essment and mitigation of unfair outcomes in algorithms\, several open sou
 rce 'fairness toolkits' recently emerged to make such methods widely acces
 sible. However\, little studied are the differences in approach and capabi
 lities of existing fairness toolkits\, and whether they are fit-for-purpos
 e in commercial contexts. Towards this\, this paper identifies the gaps be
 tween the existing open source fairness toolkit capabilities and the indus
 try practitioners' needs. Specifically\, we undertake a comparative assess
 ment of the strengths and weaknesses of six prominent open source fairness
  toolkits\, and investigate the current landscape and gaps in fairness too
 lkits through an exploratory focus group\, a semi-structured interview\, a
 nd an anonymous survey of data science/machine learning (ML) practitioners
 . We identify several gaps between the toolkits' capabilities and practiti
 oner needs\, highlighting areas requiring attention and future directions 
 towards tooling that better support 'fairness in practice'.
LOCATION:Zoom
END:VEVENT
END:VCALENDAR