shapr-package: shapr: Prediction Explanation with Dependence-Aware Shapley...

In NorskRegnesentral/shapr: Prediction Explanation with Dependence-Aware Shapley Values

shapr: Prediction Explanation with Dependence-Aware Shapley Values

Description

Complex machine learning models are often hard to interpret. However, in many situations it is crucial to understand and explain why a model made a specific prediction. Shapley values is the only method for such prediction explanation framework with a solid theoretical foundation. Previously known methods for estimating the Shapley values do, however, assume feature independence. This package implements the method described in Aas, Jullum and Løland (2019) arXiv:1903.10464, which accounts for any feature dependence, and thereby produces more accurate estimates of the true Shapley values. An accompanying Python wrapper (shaprpy) is available on GitHub.

Author(s)

Maintainer: Martin Jullum [e-mail] (ORCID)

Authors:

• Nikolai Sellereite [e-mail] (ORCID)

• Lars Henry Berge Olsen [e-mail] (ORCID)

• Annabelle Redelmeier [e-mail]

• Jon Lachmann [e-mail]

Other contributors:

• Anders Løland [e-mail] [contributor]

• Jens Christian Wahl [e-mail] [contributor]

• Camilla Lingjærde [contributor]

• Norsk Regnesentral [copyright holder, funder]

See Also

Useful links:

• https://norskregnesentral.github.io/shapr/

• https://github.com/NorskRegnesentral/shapr/

• Report bugs at https://github.com/NorskRegnesentral/shapr/issues

NorskRegnesentral/shapr documentation built on April 19, 2024, 1:19 p.m.