Fast approximative estimation of conditional Shapley values when using a linear regression model or a polynomial regression model
By: Fredrik Lohne Aanes
Potential Business Impact:
Speeds up computer learning for complex data.
We develop a new approximative estimation method for conditional Shapley values obtained using a linear regression model. We develop a new estimation method and outperform existing methodology and implementations. Compared to the sequential method in the shapr-package (i.e fit one and one model), our method runs in minutes and not in hours. Compared to the iterative method in the shapr-package, we obtain better estimates in less than or almost the same amount of time. When the number of covariates becomes too large, one can still fit thousands of regression models at once using our method. We focus on a linear regression model, but one can easily extend the method to accommodate several types of splines that can be estimated using multivariate linear regression due to linearity in the parameters.
Similar Papers
Regression-adjusted Monte Carlo Estimators for Shapley Values and Probabilistic Values
Machine Learning (CS)
Makes AI explain its decisions more accurately.
A Unified Framework for Provably Efficient Algorithms to Estimate Shapley Values
Machine Learning (CS)
Explains AI decisions more accurately and faster.
shapr: Explaining Machine Learning Models with Conditional Shapley Values in R and Python
Machine Learning (CS)
Explains why computer predictions are right or wrong.