Journal
INTERFACES
Volume 48, Issue 5, Pages 449-466Publisher
INFORMS
DOI: 10.1287/inte.2018.0957
Keywords
machine learning; sparse linear models; socring systems; trust; transparency; Interpretability; healthcare; criminal justice; recidivism
Funding
- National Science Foundation
- Philips
- Siemens
- Wistron
- Direct For Computer & Info Scie & Enginr
- Div Of Information & Intelligent Systems [1658794] Funding Source: National Science Foundation
Ask authors/readers for more resources
Questions of trust in machine-learning models are becoming increasingly important as these tools are starting to be used widely for high-stakes decisions in medicine and criminal justice. Transparency of models is a key aspect affecting trust. This paper reveals that there is new technology to build transparent machine-learning models that are often as accurate as black-box machine-learning models. These methods have already had an impact in medicine and criminal justice. This work calls into question the overall need for black-box models in these applications.
Authors
I am an author on this paper
Click your name to claim this paper and add it to your profile.
Reviews
Recommended
No Data Available