# One Model Many Scores: Using Multiverse Analysis to Prevent Fairness Hacking and Evaluate the Influence of Model Design Decisions arXiv: https://arxiv.org/abs/2308.16681 ยท HTML: https://mlsanity.com/paper/2308.16681/ ## Key facts - Cited by 12 papers in the map (data through 14 Oct 2026). - Builds on 21 of its 68 references that are in the map. - First posted on arXiv 31 Aug 2023. ## Builds on (most cited first, 21 of 21) - [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) - [A Reductions Approach to Fair Classification](https://mlsanity.com/paper/1803.02453/) (2018) - [Retiring Adult: New Datasets for Fair Machine Learning](https://mlsanity.com/paper/2108.04884/) (2021) - [A comparative study of fairness-enhancing interventions in machine learning](https://mlsanity.com/paper/1802.04422/) (2018) - [A survey on datasets for fairness-aware machine learning](https://mlsanity.com/paper/2110.00530/) (2021) - [Hyperparameter Optimization: Foundations, Algorithms, Best Practices and Open Challenges](https://mlsanity.com/paper/2107.05847/) (2021) - [Fairwashing: the risk of rationalization](https://mlsanity.com/paper/1901.09749/) (2019) - [Fairlearn: Assessing and Improving Fairness of AI Systems](https://mlsanity.com/paper/2303.16626/) (2023) - [It's COMPASlicated: The Messy Relationship between RAI Datasets and Algorithmic Fairness Benchmarks](https://mlsanity.com/paper/2106.05498/) (2021) - [Algorithmic Fairness Datasets: the Story so Far](https://mlsanity.com/paper/2202.01711/) (2022) - [Fair Bayesian Optimization](https://mlsanity.com/paper/2006.05109/) (2020) - [Arbitrariness and Social Prediction: The Confounding Role of Variance in Fair Classification](https://mlsanity.com/paper/2301.11562/) (2023) - [WEIRD FAccTs: How Western, Educated, Industrialized, Rich, and Democratic is FAccT?](https://mlsanity.com/paper/2305.06415/) (2023) - [Rethinking Bias Mitigation: Fairer Architectures Make for Fairer Face Recognition](https://mlsanity.com/paper/2210.09943/) (2022) - [The Dataset Multiplicity Problem: How Unreliable Data Impacts Predictions](https://mlsanity.com/paper/2304.10655/) (2023) - [Multi-Target Multiplicity: Flexibility and Fairness in Target Specification under Resource Constraints](https://mlsanity.com/paper/2306.13738/) (2023) - [Debiasing classifiers: is reality at variance with expectation?](https://mlsanity.com/paper/2011.02407/) (2020) - [Multi-Objective Automatic Machine Learning with AutoxgboostMC](https://mlsanity.com/paper/1908.10796/) (2019) - [Fairness in Algorithmic Profiling: A German Case Study](https://mlsanity.com/paper/2108.04134/) (2021) - [An Introduction to Algorithmic Fairness](https://mlsanity.com/paper/2105.05595/) (2021) ## Built on by (most cited first, 12 of 12) - [Systemizing Multiplicity: The Curious Case of Arbitrariness in Machine Learning](https://mlsanity.com/paper/2501.14959/) (2025) - [No Metric to Rule Them All: Toward Principled Evaluations of Graph-Learning Datasets](https://mlsanity.com/paper/2502.02379/) (2025) - [An Experimental Study on the Rashomon Effect of Balancing Methods in Imbalanced Classification](https://mlsanity.com/paper/2405.01557/) (2024) - [Robustness and Cybersecurity in the EU Artificial Intelligence Act](https://mlsanity.com/paper/2502.16184/) (2025) - [Fairness and Sparsity within Rashomon sets: Enumeration-Free Exploration and Characterization](https://mlsanity.com/paper/2502.05286/) (2025) - [Different Horses for Different Courses: Comparing Bias Mitigation Algorithms in ML](https://mlsanity.com/paper/2411.11101/) (2024) - [Bias Begins with Data: The FairGround Corpus for Robust and Reproducible Research on Algorithmic Fairness](https://mlsanity.com/paper/2510.22363/) (2025) - [Predictive Multiplicity in Survival Models: A Method for Quantifying Model Uncertainty in Predictive Maintenance Applications](https://mlsanity.com/paper/2504.12156/) (2025) - [Normative Common Ground Replication (NormCoRe): Replication-by-Translation for Studying Norms in Multi-Agent AI](https://mlsanity.com/paper/2603.11974/) (2026) - [Connecting Algorithmic Fairness to Quality Dimensions in Machine Learning in Official Statistics and Survey Production](https://mlsanity.com/paper/2402.09328/) (2024) - [A Critical Review of Predominant Bias in Neural Networks](https://mlsanity.com/paper/2502.11031/) (2025) - [ASSERT: A Measurement Pipeline for GenAI Audits](https://mlsanity.com/paper/2608.13840/) (2026) ## Abstract (arXiv) A vast number of systems across the world use algorithmic decision making (ADM) to (partially) automate decisions that have previously been made by humans. The downstream effects of ADM systems critically depend on the decisions made during a systems' design, implementation, and evaluation, as biases in data can be mitigated or reinforced along the modeling pipeline. Many of these decisions are made implicitly, without knowing exactly how they will influence the final system. To study this issue, we draw on insights from the field of psychology and introduce the method of multiverse analysis for algorithmic fairness. In our proposed method, we turn implicit decisions during design and evaluation into explicit ones and demonstrate their fairness implications. By combining decisions, we create a grid of all possible "universes" of decision combinations. For each of these universes, we compute metrics of fairness and performance. Using the resulting dataset, one can investigate the variability and robustness of fairness scores and see how and which decisions impact fairness. We demonstrate how multiverse analyses can be used to better understand fairness implications of design and evaluation decisions using an exemplary case study of predicting public health care coverage for vulnerable populations. Our results highlight how decisions regarding the evaluation of a system can lead to vastly different fairness metrics for the same model. This is problematic, as a nefarious actor could optimise or "hack" a fairness metric to portray a discriminating model as fair merely by changing how it is evaluated. We illustrate how a multiverse analysis can help to address this issue.