S
Scott M. Lundberg
Researcher at Microsoft
Publications - 58
Citations - 14799
Scott M. Lundberg is an academic researcher from Microsoft. The author has contributed to research in topics: Interpretability & Computer science. The author has an hindex of 17, co-authored 50 publications receiving 5893 citations. Previous affiliations of Scott M. Lundberg include University of Washington & Colorado State University.
Papers
More filters
Proceedings Article
A unified approach to interpreting model predictions
Scott M. Lundberg,Su-In Lee +1 more
TL;DR: In this article, a unified framework for interpreting predictions, SHAP (SHapley Additive exPlanations), is presented, which assigns each feature an importance value for a particular prediction.
Journal ArticleDOI
From Local Explanations to Global Understanding with Explainable AI for Trees.
Scott M. Lundberg,Scott M. Lundberg,Gabriel G. Erion,Hugh Chen,Alex J. DeGrave,Jordan M. Prutkin,Bala G. Nair,Ronit Katz,Jonathan Himmelfarb,Nisha Bansal,Su-In Lee +10 more
TL;DR: An explanation method for trees is presented that enables the computation of optimal local explanations for individual predictions, and the authors demonstrate their method on three medical datasets.
Posted Content
A Unified Approach to Interpreting Model Predictions
Scott M. Lundberg,Su-In Lee +1 more
TL;DR: In this paper, a unified framework for interpreting predictions, SHAP (SHapley Additive exPlanations), is presented, which assigns each feature an importance value for a particular prediction.
Journal ArticleDOI
Explainable Machine-Learning Predictions for the Prevention of Hypoxaemia During Surgery
Scott M. Lundberg,Bala G. Nair,Monica S. Vavilala,Mayumi Horibe,Michael J. Eisses,Michael J. Eisses,Trevor Adams,Trevor Adams,David E. Liston,David E. Liston,Daniel King-Wai Low,Daniel King-Wai Low,Shu-Fang Newman,Jerry Kim,Jerry Kim,Su-In Lee +15 more
TL;DR: The results suggest that if anaesthesiologists currently anticipate 15% of hypoxaemia events, with the assistance of this system they could anticipate 30%, a large portion of which may benefit from early intervention because they are associated with modifiable factors.
Posted Content
Consistent Individualized Feature Attribution for Tree Ensembles.
TL;DR: This work develops fast exact tree solutions for SHAP (SHapley Additive exPlanation) values, which are the unique consistent and locally accurate attribution values, and proposes a rich visualization of individualized feature attributions that improves over classic attribution summaries and partial dependence plots, and a unique "supervised" clustering.