본문

서브메뉴

Unfairness Detection and Evaluation in Data-Driven Decision-Making Algorithms
Unfairness Detection and Evaluation in Data-Driven Decision-Making Algorithms
Unfairness Detection and Evaluation in Data-Driven Decision-Making Algorithms

상세정보

자료유형  
 학위논문 서양
최종처리일시  
20260202103642
ISBN  
9798314873984
DDC  
004
저자명  
Li, Jinyang.
서명/저자  
Unfairness Detection and Evaluation in Data-Driven Decision-Making Algorithms
발행사항  
[Sl] : University of Michigan, 2025
발행사항  
Ann Arbor : ProQuest Dissertations & Theses, 2025
형태사항  
140 p
주기사항  
Source: Dissertations Abstracts International, Volume: 86-11, Section: B.
주기사항  
Advisor: Jagadish, H. V.
학위논문주기  
Thesis (Ph.D.)--University of Michigan, 2025.
초록/해제  
요약Recent years have witnessed a surge in the application of data-driven algorithms to assist human decision-making across various sectors, including industry, government, and non-profit organizations. Many of these applications significantly impact our daily lives. Concerns are growing about the potential biases that may be present in the data, amplified in the algorithmic processes, or introduced by the algorithms themselves. Such biases have been observed to result in injustices, particularly against specific demographic groups, highlighting the need for careful examination and correction.These concerns have given rise to a recent body of literature, which has focused primarily on biases in alphanumeric relational tables and consequent biases in labels applied in a classification task (such as who to recruit). This thesis focuses on developing efficient algorithms to detect biases within richer, more complex datasets and assesses the fairness of outcomes in algorithmic tasks beyond simple classification. Specifically, the thesis addresses the following problems:Query Refinement for Diversity Constraints: Relational queries frequently define candidate pools based on available data sources. This research develops techniques to minimally modify these relational queries, ensuring that the outcomes meet specified diversity constraints for data groups in the result set. The objective is to select diverse candidate pools without compromising the core selection criteria.Under-representation in Ranking Evaluation: This thesis introduces methods to detect hidden under-representation in algorithmic rankings without pre-defined protected groups. In particular, the thesis identifies demographic groups disproportionately under-represented in top-ranked positions.Fairness Evaluation in Data Streams: This thesis recognizes the overlooked issue of fairness measurement in dynamic environments by proposing algorithms to monitor real-time fairness metrics with time decay for classification tasks in data streams. This methodology provides a continually updated reflection of fairness, capturing evolving biases effectively.
일반주제명  
Computer science
일반주제명  
Engineering
일반주제명  
Information technology
키워드  
Algorithmic fairness
키워드  
Data-driven algorithms
키워드  
Query refinement
키워드  
Under-representation
키워드  
Data stream fairness
기타저자  
University of Michigan Computer Science & Engineering
기본자료저록  
Dissertations Abstracts International. 86-11B.
전자적 위치 및 접속  
로그인 후 원문을 볼 수 있습니다.

MARC

 008260126s2025        us                              c    eng  d
■001000017358086
■00520260202103642
■006m          o    d                
■007cr#unu||||||||
■020    ▼a9798314873984
■035    ▼a(MiAaPQ)AAI32092550
■035    ▼a(MiAaPQ)umichrackham006076
■040    ▼aMiAaPQ▼cMiAaPQ
■0820  ▼a004
■1001  ▼aLi,  Jinyang.
■24510▼aUnfairness  Detection  and  Evaluation  in  Data-Driven  Decision-Making  Algorithms
■260    ▼a[Sl]▼bUniversity  of  Michigan▼c2025
■260  1▼aAnn  Arbor▼bProQuest  Dissertations  &  Theses▼c2025
■300    ▼a140  p
■500    ▼aSource:  Dissertations  Abstracts  International,  Volume:  86-11,  Section:  B.
■500    ▼aAdvisor:  Jagadish,  H.  V.
■5021  ▼aThesis  (Ph.D.)--University  of  Michigan,  2025.
■520    ▼aRecent  years  have  witnessed  a  surge  in  the  application  of  data-driven  algorithms  to  assist  human  decision-making  across  various  sectors,  including  industry,  government,  and  non-profit  organizations.  Many  of  these  applications  significantly  impact  our  daily  lives.  Concerns  are  growing  about  the  potential  biases  that  may  be  present  in  the  data,  amplified  in  the  algorithmic  processes,  or  introduced  by  the  algorithms  themselves.  Such  biases  have  been  observed  to  result  in  injustices,  particularly  against  specific  demographic  groups,  highlighting  the  need  for  careful  examination  and  correction.These  concerns  have  given  rise  to  a  recent  body  of  literature,  which  has  focused  primarily  on  biases  in  alphanumeric  relational  tables  and  consequent  biases  in  labels  applied  in  a  classification  task  (such  as  who  to  recruit).  This  thesis  focuses  on  developing  efficient  algorithms  to  detect  biases  within  richer,  more  complex  datasets  and  assesses  the  fairness  of  outcomes  in  algorithmic  tasks  beyond  simple  classification.  Specifically,  the  thesis  addresses  the  following  problems:Query  Refinement  for  Diversity  Constraints:  Relational  queries  frequently  define  candidate  pools  based  on  available  data  sources.  This  research  develops  techniques  to  minimally  modify  these  relational  queries,  ensuring  that  the  outcomes  meet  specified  diversity  constraints  for  data  groups  in  the  result  set.  The  objective  is  to  select  diverse  candidate  pools  without  compromising  the  core  selection  criteria.Under-representation  in  Ranking  Evaluation:  This  thesis  introduces  methods  to  detect  hidden  under-representation  in  algorithmic  rankings  without  pre-defined  protected  groups.  In  particular,  the  thesis  identifies  demographic  groups  disproportionately  under-represented  in  top-ranked  positions.Fairness  Evaluation  in  Data  Streams:  This  thesis  recognizes  the  overlooked  issue  of  fairness  measurement  in  dynamic  environments  by  proposing  algorithms  to  monitor  real-time  fairness  metrics  with  time  decay  for  classification  tasks  in  data  streams.  This  methodology  provides  a  continually  updated  reflection  of  fairness,  capturing  evolving  biases  effectively.
■590    ▼aSchool  code:  0127.
■650  4▼aComputer  science
■650  4▼aEngineering
■650  4▼aInformation  technology
■653    ▼aAlgorithmic  fairness
■653    ▼aData-driven  algorithms
■653    ▼aQuery  refinement
■653    ▼aUnder-representation
■653    ▼aData  stream  fairness
■690    ▼a0984
■690    ▼a0489
■690    ▼a0800
■690    ▼a0537
■71020▼aUniversity  of  Michigan▼bComputer  Science  &  Engineering.
■7730  ▼tDissertations  Abstracts  International▼g86-11B.
■790    ▼a0127
■791    ▼aPh.D.
■792    ▼a2025
■793    ▼aEnglish
■85640▼uhttp://www.riss.kr/pdu/ddodLink.do?id=T17358086▼nKERIS▼z이  자료의  원문은  한국교육학술정보원에서  제공합니다.

미리보기

내보내기

chatGPT토론

Ai 추천 관련 도서


    신착도서 더보기
    최근 3년간 통계입니다.

    소장정보

    • 예약
    • 소재불명신고
    • 나의폴더
    • 우선정리요청
    • 비도서대출신청
    • 야간 도서대출신청
    소장자료
    등록번호 청구기호 소장처 대출가능여부 대출정보
    TF15778 전자도서 대출가능 마이폴더 부재도서신고 비도서대출신청 야간 도서대출신청

    * 대출중인 자료에 한하여 예약이 가능합니다. 예약을 원하시면 예약버튼을 클릭하십시오.

    해당 도서를 다른 이용자가 함께 대출한 도서

    관련 인기도서

    로그인 후 이용 가능합니다.