Bibliography

1. Štrumbelj, Erik, and Igor Kononenko. "Explaining prediction models and individual predictions with feature contributions." Knowledge and information systems 41.3 (2014): 647-665
2. Kjersti Aas, Martin Jullum and Anders Løland. Explaining individual predictions when features are dependent: More accurate approximations to Shapley values arXiv:1903.10464
3. Lundberg, Scott and Lee, Su-In. "A Unified Approach to Interpreting Model Predictions" arXiv:1705.07874
4. Lundberg, Scott and Erion, Gabriel and Lee, Su-In. "Consistent Individualized Feature Attribution for Tree Ensembles" arXiv:1802.03888

Additional Resources

• Interpretable Machine Learning, an HTML book by Christopher Molnar.
• shap is a Python package for computing Shapley values and some similar feature importance values using a wide variety of methods.