A General Method for Visualizing and Explaining Black-Box Regression Models

54 citations recorded by the source corpus.

How researchers see this paper

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

Visualizing the Feature Importance for Black Box Models (2018, methodology): “A method that measures feature effects based on the Shapley value [19] from coalitional game theory was first presented for classification in [21] and has been extended to regression and global analysis in [22].”
Explanations of model predictions with live and breakDown packages (2018, methodology): “Find some examples in Štrumbelj and Kononenko (2011); Tzeng and Ma (2005); Zeiler and Fergus (2014).”
Peeking Inside the Black Box: Visualizing Statistical Learning With Plots of Individual Conditional Expectation (2013, methodology): “Further, for a single out-of-sample observation, plotting an ICE curve for each predictor can illustrate the sensitivity of the ﬁtted value to changes in each predictor for this particular observation, which is the goal of the “contribution plots” of Strumbelj and Kononenko (2011).”
Explaining prediction models and individual predictions with feature contributions (2014, background): “As shown in [29], it is sufficient to limit ourselves to such distributions”
Explanation and Reliability of Individual Predictions (2013, methodology): “We adopt, with minor modiﬁcations, the notation used in [30].”