Dear all BigInsighters,

The next EXPLAINING AI SEMINAR will take place online:

Speakers: Annabelle Redelmeier and Martin Jullum, NR

Location: Join Microsoft Teams Meeting

Title: Explaining predictive models with mixed features using Shapley values and conditional inference trees

Abstract: Shapley values stand out as a sound method to explain predictions from any type of machine learning model. The original development of Shapley values for prediction explanation relied on the assumption that the features being described were independent. This methodology was then extended to explain dependent features with an underlying continuous distribution. We propose a method to explain mixed (i.e. continuous, discrete, ordinal, and categorical) dependent features by modeling the dependence structure of the features using conditional inference trees. We demonstrate our proposed method against the current industry standards in various simulation studies and that our method often outperforms the other approaches.

The paper is available here: https://arxiv.org/abs/2007.01027

There is also an accompanying R package called shapr: "Explaining the output of machine learning models with more accurately estimated Shapley values" available at https://github.com/NorskRegnesentral/shapr

Annabelle will present the method, Martin will present the shapr package and there will be a short discussion.

Presentation Slides: https://www.nr.no/~anderslo/BI_seminar-03-09-2020_2.pdf

Package slides:

https://www.dropbox.com/s/wfdczjoe3t0bfs2/presentation_print.html?dl=1

Welcome!
Anders Løland