# Explainable Machine Learning for Public Policy: Use Cases, Gaps, and Research Directions

arXiv: https://arxiv.org/abs/2010.14374 · HTML: https://mlsanity.com/paper/2010.14374/

## Key facts

- Cited by 17 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 27 Oct 2020.

## Built on by (most cited first, 17 of 17)

- [How can I choose an explainer? An Application-grounded Evaluation of Post-hoc Explanations](https://mlsanity.com/paper/2101.08758/) (2021)
- [Most Influential Subset Selection: Challenges, Promises, and Beyond](https://mlsanity.com/paper/2409.18153/) (2024)
- [Fairness in Algorithmic Recourse Through the Lens of Substantive Equality of Opportunity](https://mlsanity.com/paper/2401.16088/) (2024)
- [Probabilistic Stability Guarantees for Feature Attributions](https://mlsanity.com/paper/2504.13787/) (2025)
- [Think About the Stakeholders First! Towards an Algorithmic Transparency Playbook for Regulatory Compliance](https://mlsanity.com/paper/2207.01482/) (2022)
- [Desiderata for Explainable AI in statistical production systems of the European Central Bank](https://mlsanity.com/paper/2107.08045/) (2021)
- [Explainable Artificial Intelligence: Precepts, Methods, and Opportunities for Research in Construction](https://mlsanity.com/paper/2211.06579/) (2022)
- [A Case Study on Designing Evaluations of ML Explanations with Simulated User Studies](https://mlsanity.com/paper/2302.07444/) (2023)
- [Need of AI in Modern Education: in the Eyes of Explainable AI (xAI)](https://mlsanity.com/paper/2408.00025/) (2024)
- [GeoReg: Weight-Constrained Few-Shot Regression for Socio-Economic Estimation using LLM](https://mlsanity.com/paper/2507.13323/) (2025)
- [One-way Explainability Isn't The Message](https://mlsanity.com/paper/2205.08954/) (2022)
- [On the Importance of Application-Grounded Experimental Design for Evaluating Explainable ML Methods](https://mlsanity.com/paper/2206.13503/) (2022)
- [Explainable Artificial Intelligence in Construction: The Content, Context, Process, Outcome Evaluation Framework](https://mlsanity.com/paper/2211.06561/) (2022)
- [Five policy uses of algorithmic transparency and explainability](https://mlsanity.com/paper/2302.03080/) (2023)
- [Beyond XAI:Obstacles Towards Responsible AI](https://mlsanity.com/paper/2309.03638/) (2023)
- [How to Achieve Higher Accuracy with Less Training Points?](https://mlsanity.com/paper/2504.13586/) (2025)
- [Crowd-Sourced Geographies of Income: Using Google Maps Points of Interest as High-Frequency Proxies for Sub-Municipal Income Estimation in Sao Paulo, Brazil](https://mlsanity.com/paper/2608.07871/) (2026)

## Abstract (arXiv)

Explainability is highly-desired in Machine Learning (ML) systems supporting high-stakes policy decisions in areas such as health, criminal justice, education, and employment. While the field of explainable ML has expanded in recent years, much of this work has not taken real-world needs into account. A majority of proposed methods are designed with textitgeneric explainability goals without well-defined use-cases or intended end-users and evaluated on simplified tasks, benchmark problems/datasets, or with proxy users (e.g., AMT). We argue that these simplified evaluation settings do not capture the nuances and complexities of real-world applications. As a result, the applicability and effectiveness of this large body of theoretical and methodological work in real-world applications are unclear. In this work, we take steps toward addressing this gap for the domain of public policy. First, we identify the primary use-cases of explainable ML within public policy problems. For each use case, we define the end-users of explanations and the specific goals the explanations have to fulfill. Finally, we map existing work in explainable ML to these use-cases, identify gaps in established capabilities, and propose research directions to fill those gaps to have a practical societal impact through ML. The contribution is 1) a methodology for explainable ML researchers to identify use cases and develop methods targeted at them and 2) using that methodology for the domain of public policy and giving an example for the researchers on developing explainable ML methods that result in real-world impact.