Towards User Guided Actionable Recourse

被引:1
|
作者
Yetukuri, Jayanth [1 ]
Hardy, Ian [1 ]
Liu, Yang [1 ]
机构
[1] Univ Calif Santa Cruz, Santa Cruz, CA 95064 USA
基金
美国国家科学基金会;
关键词
Actionable recourse; User preference;
D O I
10.1145/3600211.3604708
中图分类号
TP18 [人工智能理论];
学科分类号
081104 ; 0812 ; 0835 ; 1405 ;
摘要
Machine Learning's proliferation in critical fields such as healthcare, banking, and criminal justice has motivated the creation of tools which ensure trust and transparency in ML models. One such tool is Actionable Recourse (AR) for negatively impacted users. AR describes recommendations of cost-efficient changes to a user's actionable features to help them obtain favorable outcomes. Existing approaches for providing recourse optimize for properties such as proximity, sparsity, validity, and distance-based costs. However, an often-overlooked but crucial requirement for actionability is a consideration of User Preference to guide the recourse generation process. In this work, we attempt to capture user preferences via soft constraints in three simple forms: i) scoring continuous features, ii) bounding feature values and iii) ranking categorical features. Finally, we propose a gradient-based approach to identify User Preferred Actionable Recourse (UP-AR). We carried out extensive experiments to verify the effectiveness of our approach.
引用
下载
收藏
页码:742 / 751
页数:10
相关论文
共 50 条
  • [21] Understanding the User Perception and Experience of Interactive Algorithmic Recourse Customization
    Koh, Seungh un
    Kim, Byung hyung
    Jo, Sungho
    ACM TRANSACTIONS ON COMPUTER-HUMAN INTERACTION, 2024, 31 (03)
  • [22] Towards User-Guided Quantitative Evaluation of Wrist Fractures in CT Images
    Nysjo, Johan
    Christersson, Albert
    Malmberg, Filip
    Sintorn, Ida-Maria
    Nystrom, Ingela
    COMPUTER VISION AND GRAPHICS, 2012, 7594 : 204 - 211
  • [23] Towards a User-Guided Difference-based Detection of Atomic Changes
    Khelladi, Djamel Eddine
    Bendraou, Reda
    Gervais, Marie-Pierre
    2016 21ST INTERNATIONAL CONFERENCE ON ENGINEERING OF COMPLEX COMPUTER SYSTEMS (ICECCS 2016), 2016, : 211 - 214
  • [24] Towards Actionable Learning Analytics Using Dispositions
    Tempelaar, Dirk T.
    Rienties, Bart
    Quan Nguyen
    IEEE TRANSACTIONS ON LEARNING TECHNOLOGIES, 2017, 10 (01): : 6 - 16
  • [25] Explanatory Dialogs: Towards Actionable, Interactive Explanations
    Bansal, Gagan
    PROCEEDINGS OF THE 2018 AAAI/ACM CONFERENCE ON AI, ETHICS, AND SOCIETY (AIES'18), 2018, : 356 - 357
  • [26] Towards actionable risk stratification: A bilinear approach
    Wang, Xiang
    Wang, Fei
    Hu, Jianying
    Sorrentino, Robert
    JOURNAL OF BIOMEDICAL INFORMATICS, 2015, 53 : 147 - 155
  • [27] Communicating actionable user research for human-centered design
    Roschuni, Celeste
    Goodman, Elizabeth
    Agogino, Alice M.
    AI EDAM-ARTIFICIAL INTELLIGENCE FOR ENGINEERING DESIGN ANALYSIS AND MANUFACTURING, 2013, 27 (02): : 143 - 154
  • [28] User Feedback and Uncertainty in User Guided Binarization
    Westphal, Florian
    Grahn, Hakan
    Lavesson, Niklas
    2018 18TH IEEE INTERNATIONAL CONFERENCE ON DATA MINING WORKSHOPS (ICDMW), 2018, : 403 - 410
  • [29] Towards clinically actionable digital phenotyping targets in schizophrenia
    Henson, Philip
    Barnett, Ian
    Keshavan, Matcheri
    Torous, John
    NPJ SCHIZOPHRENIA, 2020, 6 (01):
  • [30] Towards clinically actionable digital phenotyping targets in schizophrenia
    Philip Henson
    Ian Barnett
    Matcheri Keshavan
    John Torous
    npj Schizophrenia, 6