Explaining prediction models and individual predictions with feature contributions

Explore this paper's citation graph

Summary

A sensitivity analysis-based method for explaining prediction models that can be applied to any type of classification or regression model, and which is equivalent to commonly used additive model-specific methods when explaining an additive model.

Type
article
Published
2014-12-01
Cited by
2,202
References
50

Keywords

Computer science, Artificial intelligence, Feature (linguistics), Machine learning, Sensitivity (control systems)

References

Cited by

Related papers