Optimized Scoring Systems: Toward Trust in Machine Learning for Healthcare and Criminal Justice

By Cynthia Rudin, Berk Ustun. 2018

121 citations recorded by the source corpus.

The authors developed and implemented transparent machine-learning models that call into question the use of black-box machine-learning models in healthcare and criminal justice applications.

Subfields: Artificial Intelligence, AI Ethics, Fairness & Society

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Artificial Intelligence

In AI Ethics, Fairness & Society

Citations in the corpus

Interpretable Machine Learning: Fundamental Principles and 10 Grand Challenges (2021, methodology): “There are several methods that can solve (3) directly (Ustun et al., 2013; Ustun and Rudin, 2016, 2017, 2019; Rudin and Ustun, 2018).”
Please Stop Explaining Black Box Models for High Stakes Decisions (2018, methodology): “Figure 4: Scoring system for risk of recidivism from Rudin and Ustun [2018] [which grew out of Ustun and Rudin, 2017, Zeng et al., 2017, Ustun and Rudin, 2015].”
Why Are We Using Black Box Models in AI When We Don’t Need To? A Lesson From An Explainable AI Competition (2019, background): “…domains and across many other high-stakes machine learning applications where life-altering decisions are being made (e.g., Caruana et al., 2015; Razavian et al., 2015; Rudin & Ustun, 2018, who all show models with interpretability constraints that perform just as well as unconstrained models).”
Machine Learning Interpretability: A Survey on Methods and Metrics (2019, background): “These include decision sets [113], rule-based classifiers [114–117], and scorecards [37,118].”
Transparency: Motivations and Challenges (2017, background): “tings, a global model which is constrained to be ‘interpretable by construction’, for example by being described by a simple, short, intuitive scoring system, will provide suciently high performance [58]. We discuss further notions of understanding in Section 7. Highlighting a key challenge even for”
Explainable AI under contract and tort law: legal incentives and technical challenges (2020, background): “However, a number of studies have shown that it is often possible to identify ex post the features (input variables) that are responsible for a specific output (Samek et al. 2017; Montavon et al. 2017; Bach et al. 2015; Lapuschkin et al. 2019; Ribeiro et al. 2016).”