BEGIN:VCALENDAR
VERSION:2.0
PRODID:-//Memento EPFL//
BEGIN:VEVENT
SUMMARY:Detecting Algorithmic Discrimination
DTSTART:20170714T093000
DTEND:20170714T103000
DTSTAMP:20260406T161445Z
UID:24b7d067691a23f1a35915f0187f6c40d729cb2c58ac1a57c35e9601
CATEGORIES:Conferences - Seminars
DESCRIPTION:Carlos Castillo http://chato.cl/research/\nAlgorithms and deci
 sion making based on Big Data have become pervasive in all aspects of our 
 daily (offline and online) lives\, as they have become essential tools in 
 personal finance\, health care\, hiring\, housing\, education\, and polici
 es. Data and algorithms determine the media we consume\, the stories we re
 ad\, the people we meet\, the places we visit\, but also whether we get a 
 job\, or whether our loan request is approved. It is therefore of societal
  and ethical importance to ask whether these algorithms can be discriminat
 ive on grounds\, such as gender\, ethnicity\, marital or health status. It
  turns out that the answer is positive: for instance\, recent studies have
  shown that Google’s online advertising system displayed ads for high-in
 come jobs to men much more often than it did to women.\n\nThis algorithmic
  bias exists even when there is no discrimination intention in the develop
 er of the algorithm. Sometimes it may be inherent to the data sources used
  (software making decisions based on data can reflect\, or even amplify\, 
 the results of historical discrimination)\, but even when the sensitive at
 tributes have been suppressed from the input\, a well trained machine lear
 ning algorithm may still discriminate on the basis of such sensitive attri
 butes because of correlations existing in the data.\n\nFrom technical poin
 t of view\, efforts at fighting algorithmic bias have led to developing tw
 o groups of solutions: (1) techniques for discrimination discovery from da
 ta and (2) discrimination prevention by means of fairness-aware data minin
 g\, develop data mining systems which are discrimination-conscious by-desi
 gn. In this talk we mainly focus on the first groups of solutions: In the 
 first part\, we will present some examples of algorithmic bias\, followed 
 by introducing the sources of algorithmic discrimination\, legal principle
 s and definitions and finally measures of discrimination applied in fairne
 ss-aware data mining solutions. In the second part\, we will introduce som
 e of the recent data mining and machine learning approaches for discoverin
 g discrimination from the database of historical decision records. \n\nTh
 is talk is joint work with Sara Hajian and Francesco Bonchi\, and an exten
 ded version of it was presented as a KDD 2016 tutorial: http://francescobo
 nchi.com/algorithmic_bias_tutorial.html\n\nCarlos Castillo is Director of 
 Research for Data Science at Eurecat. He is a web miner with a background 
 on information retrieval\, and has been influential in the areas of web co
 ntent quality and credibility\, and adversarial web search. He is a prolif
 ic researcher with more than 75 publications in top-tier international con
 ferences and journals\, receiving 9900+ citations. His works include a rec
 ent book on Big Crisis Data\, as well as monographs on Information and Inf
 luence Propagation\, and Adversarial Web Search.\n\nCarlos received his Ph
 .D from the University of Chile (2004)\, and was a visiting scientist at U
 niversitat Pompeu Fabra (2005) and Sapienza Universitá di Roma (2006) bef
 ore working as a scientist and senior scientist at Yahoo! Research (2006-2
 012)\, and as a senior scientist and principal scientist at Qatar Computin
 g Research Institute (2012-2015). He has served in the Program Committee (
 PC) or Senior PC (SPC) of all major conferences in his area (WWW\, WSDM\, 
 SIGIR\, KDD\, CIKM\, etc.)\, and is part of the editorial committee of Tra
 nsactions on the Web and Internet Research. He is PC Co-Chair of ACM Digit
 al Health 2017 and was PC Co-Chair of 2016\, and of WSDM 2014\; co-organiz
 ed the Adversarial Information Retrieval Workshop and Web Spam Challenge i
 n 2007 and 2008\, the ECML/PKDD Discovery Challenge in 2010 and 2014\, the
  Web Quality Workshop from 2011 to 2014\, and the Social Web for Disaster 
 Management Workshop in 2015 and 2016. He is an accredited advanced researc
 her (as required to be a full professor) by AQU in Catalonia\, an ACM Seni
 or Member\, and an IEEE Senior Member.
LOCATION:BC 420 https://plan.epfl.ch/?room==BC%20420
STATUS:CONFIRMED
END:VEVENT
END:VCALENDAR