# Stream-Based Monitoring of Algorithmic Fairness

arXiv: https://arxiv.org/abs/2501.18331 · HTML: https://mlsanity.com/paper/2501.18331/

## Key facts

- Cited by 5 papers in the map (data through 14 Oct 2026).
- Builds on 20 of its 44 references that are in the map.
- First posted on arXiv 30 Jan 2025.

## Builds on (most cited first, 20 of 20)

- [Equality of Opportunity in Supervised Learning](https://mlsanity.com/paper/1610.02413/) (2016)
- [A Survey on Bias and Fairness in Machine Learning](https://mlsanity.com/paper/1908.09635/) (2019)
- [Counterfactual Fairness](https://mlsanity.com/paper/1703.06856/) (2017)
- [Certifying and removing disparate impact](https://mlsanity.com/paper/1412.3756/) (2014)
- [A Reductions Approach to Fair Classification](https://mlsanity.com/paper/1803.02453/) (2018)
- [Algorithmic decision making and the cost of fairness](https://mlsanity.com/paper/1701.08230/) (2017)
- [Algorithmic Fairness](https://mlsanity.com/paper/2001.09784/) (2020)
- [Automated Directed Fairness Testing](https://mlsanity.com/paper/1807.00468/) (2018)
- [Learning Certified Individually Fair Representations](https://mlsanity.com/paper/2002.10312/) (2020)
- [Probabilistic Verification of Fairness Properties via Concentration](https://mlsanity.com/paper/1812.02573/) (2018)
- [Runtime Monitoring of Dynamic Fairness Properties](https://mlsanity.com/paper/2305.04699/) (2023)
- [Monitoring Algorithmic Fairness](https://mlsanity.com/paper/2305.15979/) (2023)
- [Monitoring Algorithmic Fairness under Partial Observations](https://mlsanity.com/paper/2308.00341/) (2023)
- [A Survey on the Evolution of Stream Processing Systems](https://mlsanity.com/paper/2008.00842/) (2020)
- [Fairness Shields: Safeguarding against Biased Decision Makers](https://mlsanity.com/paper/2412.11994/) (2024)
- [TeSSLa: Temporal Stream-based Specification Language](https://mlsanity.com/paper/1808.10717/) (2018)
- [Leveraging Static Analysis: An IDE for RTLola](https://mlsanity.com/paper/2311.08096/) (2023)
- [Monitoring Unmanned Aircraft: Specification, Integration, and Lessons-learned](https://mlsanity.com/paper/2404.12035/) (2024)
- [RTLola Cleared for Take-Off: Monitoring Autonomous Aircraft](https://mlsanity.com/paper/2004.06488/) (2020)
- [An Information-Flow Perspective on Algorithmic Fairness](https://mlsanity.com/paper/2312.10128/) (2023)

## Built on by (most cited first, 5 of 5)

- [Continuous Fairness On Data Streams](https://mlsanity.com/paper/2601.08976/) (2026)
- [Energy Shields for Fairness](https://mlsanity.com/paper/2605.24926/) (2026)
- [Consensus vs. Dissent: Dynamic LLM Modeling of Subjective Preferences in Group Recommenders](https://mlsanity.com/paper/2607.10235/) (2026)
- [Evaluating Model Retraining under Drift: Paired Comparisons of Cumulative Subgroup Disparity](https://mlsanity.com/paper/2609.09788/) (2026)
- [FairMon: A Tool for Monitoring and Visualizing Algorithmic Fairness](https://mlsanity.com/paper/2609.26123/) (2026)

## Abstract (arXiv)

Automatic decision and prediction systems are increasingly deployed in applications where they significantly impact the livelihood of people, such as for predicting the creditworthiness of loan applicants or the recidivism risk of defendants. These applications have given rise to a new class of algorithmic-fairness specifications that require the systems to decide and predict without bias against social groups. Verifying these specifications statically is often out of reach for realistic systems, since the systems may, e.g., employ complex learning components, and reason over a large input space. In this paper, we therefore propose stream-based monitoring as a solution for verifying the algorithmic fairness of decision and prediction systems at runtime. Concretely, we present a principled way to formalize algorithmic fairness over temporal data streams in the specification language RTLola and demonstrate the efficacy of this approach on a number of benchmarks. Besides synthetic scenarios that particularly highlight its efficiency on streams with a scaling amount of data, we notably evaluate the monitor on real-world data from the recidivism prediction tool COMPAS.