8  Explaining predictions

In this chapter, we will

navigate the accuracy-explainability for public policy Bell et al. (2022)

what is explainable differs between stakeholders Amarasinghe et al. (2023)

biodiversity need sustained model uptake Weiskopf et al. (2022)

Štrumbelj and Kononenko (2013) monte carlo approximation of shapley values

Wadoux, Saby, and Martin (2023) mapping of shapley values

Mesgaran, Cousens, and Webber (2014) mapping of most important covariates

Lundberg and Lee (2017) SHAP

transfo in model = we can still apply these techniques instead of asking “what does PC1 = 0.4 mean”

References

Amarasinghe, Kasun, Kit T. Rodolfa, Hemank Lamba, and Rayid Ghani. 2023. “Explainable Machine Learning for Public Policy: Use Cases, Gaps, and Research Directions.” Data & Policy 5. https://doi.org/10.1017/dap.2023.2.

Bell, Andrew, Ian Solano-Kamaiko, Oded Nov, and Julia Stoyanovich. 2022. “It’s Just Not That Simple: An Empirical Study of the Accuracy-Explainability Trade-Off in Machine Learning for Public Policy.” 2022 ACM Conference on Fairness, Accountability, and Transparency, June. https://doi.org/10.1145/3531146.3533090.

Lundberg, Scott M, and Su-In Lee. 2017. “A Unified Approach to Interpreting Model Predictions.” In Advances in Neural Information Processing Systems, edited by I. Guyon, U. Von Luxburg, S. Bengio, H. Wallach, R. Fergus, S. Vishwanathan, and R. Garnett. Vol. 30. Curran Associates, Inc. https://proceedings.neurips.cc/paper_files/paper/2017/file/8a20a8621978632d76c43dfd28b67767-Paper.pdf.

Mesgaran, Mohsen B., Roger D. Cousens, and Bruce L. Webber. 2014. “Here Be Dragons: A Tool for Quantifying Novelty Due to Covariate Range and Correlation Change When Projecting Species Distribution Models.” Edited by Janet Franklin. Diversity and Distributions 20 (10): 1147–59. https://doi.org/10.1111/ddi.12209.

Štrumbelj, Erik, and Igor Kononenko. 2013. “Explaining Prediction Models and Individual Predictions with Feature Contributions.” Knowledge and Information Systems 41 (3): 647–65. https://doi.org/10.1007/s10115-013-0679-x.

Wadoux, Alexandre M. J.-C., Nicolas P. A. Saby, and Manuel P. Martin. 2023. “Shapley Values Reveal the Drivers of Soil Organic Carbon Stock Prediction.” SOIL 9 (1): 21–38. https://doi.org/10.5194/soil-9-21-2023.

Weiskopf, Sarah R., Zuzana V. Harmáčková, Ciara G. Johnson, María Cecilia Londoño-Murcia, Brian W. Miller, Bonnie J. E. Myers, Laura Pereira, et al. 2022. “Increasing the Uptake of Ecological Model Results in Policy Decisions to Improve Biodiversity Outcomes.” Environmental Modelling & Software 149 (March): 105318. https://doi.org/10.1016/j.envsoft.2022.105318.