TY - JOUR
T1 - Toward a taxonomy of trust for probabilistic machine learning
AU - Broderick, Tamara
AU - Gelman, Andrew
AU - Meager, Rachael
AU - Smith, Anna L.
AU - Zheng, Tian
N1 - Publisher Copyright:
© 2023 The Authors.
PY - 2023/2
Y1 - 2023/2
N2 - Probabilistic machine learning increasingly informs critical decisions in medicine, economics, politics, and beyond. To aid the development of trust in these decisions, we develop a taxonomy delineating where trust in an analysis can break down: (i) in the translation of real-world goals to goals on a particular set of training data, (ii) in the translation of abstract goals on the training data to a concrete mathematical problem, (iii) in the use of an algorithm to solve the stated mathematical problem, and (iv) in the use of a particular code implementation of the chosen algorithm. We detail how trust can fail at each step and illustrate our taxonomy with two case studies. Finally, we describe a wide variety of methods that can be used to increase trust at each step of our taxonomy. The use of our taxonomy highlights not only steps where existing research work on trust tends to concentrate and but also steps where building trust is particularly challenging.
AB - Probabilistic machine learning increasingly informs critical decisions in medicine, economics, politics, and beyond. To aid the development of trust in these decisions, we develop a taxonomy delineating where trust in an analysis can break down: (i) in the translation of real-world goals to goals on a particular set of training data, (ii) in the translation of abstract goals on the training data to a concrete mathematical problem, (iii) in the use of an algorithm to solve the stated mathematical problem, and (iv) in the use of a particular code implementation of the chosen algorithm. We detail how trust can fail at each step and illustrate our taxonomy with two case studies. Finally, we describe a wide variety of methods that can be used to increase trust at each step of our taxonomy. The use of our taxonomy highlights not only steps where existing research work on trust tends to concentrate and but also steps where building trust is particularly challenging.
UR - http://www.scopus.com/inward/record.url?scp=85148114423&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=85148114423&partnerID=8YFLogxK
U2 - 10.1126/sciadv.abn3999
DO - 10.1126/sciadv.abn3999
M3 - Review article
C2 - 36791188
AN - SCOPUS:85148114423
VL - 9
JO - Science advances
JF - Science advances
IS - 7
M1 - eabn3999
ER -