AI Fairness 360: An extensible toolkit for detecting and mitigating algorithmic bias
The DOI matches its Crossref record; 28 of the 31 references it cites were found in a registry or an index.
Abstract
Fairness is an increasingly important concern as machine learning models are used to support decision making in high-stakes applications such as mortgage lending, hiring, and prison sentencing. This article introduces a new open-source Python toolkit for algorithmic fairness, AI Fairness 360 (AIF360), released under an Apache v2.0 license (https://github.com/ibm/aif360). The main objectives of this toolkit are to help facilitate the transition of fairness research algorithms for use in an industrial setting and to provide a common framework for fairness researchers to share and evaluate algorithms. The package includes a comprehensive set of fairness metrics for datasets and models, explanations for these metrics, and algorithms to mitigate bias in datasets and models. It also includes an interactive Web experience that provides a gentle introduction to the concepts and capabilities for line-of-business users, researchers, and developers to extend the toolkit with their new algorithms and improvements and to use it for performance benchmarking. A built-in testing infrastructure maintains code quality.
Overview
The claims and statistics of this paper haven’t been checked yet.
Free: it reads the open-access text and checks the first 5 claims that cite a source we can check. Create a free account to check every claim.
Integrity signals
Registry
Cites
Statistics
Verification
Claims the paper makes
The claims and statistics of this paper haven’t been checked yet.
Free: it reads the open-access text and checks the first 5 claims that cite a source we can check. Create a free account to check every claim.
Claims other papers make about this one
Each is checked against this paper’s own text: does it say what the citing paper says it does?
The source backs part of the claim, not all of it — or backs it for a different population, condition or comparison.
In the citing paper
“the Linux Foundation, which hosts several of the open source tools we found (IBM's AI Fairness 360 [15], for example).”
From Towards AI Accountability Infrastructure: Gaps and Opportunities in AI Audit Tooling (2025) · cites this paper as [15]
Experimental — accuracy not yet measuredThe cited source says what the claim attributes to it.
In the citing paper
“An open-source toolkit, the AI Fairness 360, is available to help AI researchers examine, report, and mitigate discrimination and bias in machine learning models throughout the AI development lifecycle [52].”
From Bias in artificial intelligence algorithms and recommendations for mitigation (2023) · cites this paper as [52]
The cited source says what the claim attributes to it.
In the citing paper
“It includes a comprehensive set of metrics for datasets and models to test for biases, explanations for those metrics, and algorithms to mitigate bias in datasets and models.”
From Bias in artificial intelligence algorithms and recommendations for mitigation (2023) · cites this paper as [52]
The cited source says what the claim attributes to it.
In the citing paper
“If bias is discovered in an algorithm, a variety of solutions are now available to help mitigate and reduce the level of bias (Bellamy et al., 2019).”
From Addressing Fairness, Bias, and Appropriate Use of Artificial Intelligence and Machine Learning in Global Health (2021) · cites this paper as Bellamy et al., 2019
The cited source says what the claim attributes to it.
In the citing paper
“Various toolboxes have been released in the past years to assist the algorithm experimentation and software development to enhance AI trustworthiness in different aspects such as fairness [12, 13, 71], XAI [56, 1, 8], and adversarial robustness [55, 2].”
From Trustworthy AI: From Principles to Practices (2023) · cites this paper as [12]
4 more claims about this paper
Create a free account to see every claim other papers make about this one.
Self-check
Percentages, sums and reported differences re-computed from the paper’s own numbers.
The self-check needs the paper’s full text.
Citations
Cites
UCI Machine Learning Repository
Asuncion, A. (2007) · Medical Entomology and Zoology · Cited by 25,410
Equality of Opportunity in Supervised Learning
Hardt, M., Price, E., & Srebro, N. (2016) · arXiv · doi:10.48550/arxiv.1610.02413 · Cited by 2,536
Certifying and Removing Disparate Impact
Feldman, M., Friedler, S. A., Moeller, J., Scheidegger, C., & Venkatasubramanian, S. (2015) · Proceedings of the 21th ACM SIGKDD International Conference on Knowledge Discovery and Data Mining · doi:10.1145/2783258.2783311 · Cited by 1,827
Mitigating Unwanted Biases with Adversarial Learning
Zhang, B. H., Lemoine, B., & Mitchell, M. (2018) · Proceedings of the 2018 AAAI/ACM Conference on AI, Ethics, and Society · doi:10.1145/3278721.3278779 · Cited by 1,387
Data preprocessing techniques for classification without discrimination
Kamiran, F., & Calders, T. (2012) · Knowledge and Information Systems · doi:10.1007/s10115-011-0463-8 · Cited by 1,305
(2013) · Cited by 1,126
Counterfactual explanations without opening the black box: automated decisions and the GDPR
Wachter, S., Mittelstadt, B., & Russell, C. (2017) · SSRN Electronic Journal · doi:10.2139/ssrn.3063289 · Cited by 1,061
Kusner, M. J., Loftus, J. R., Russell, C., & Silva, R. (2017) · arXiv · doi:10.48550/arxiv.1703.06856 · Cited by 995
Optimized Pre-Processing for Discrimination Prevention
Calmon, F. P., Wei, D., Vinzamuri, B., Ramamurthy, K. N., & Varshney, K. R. (2017) · neural information processing systems · Cited by 978
Self-citationInherent trade-offs in the fair determination of risk scores
Kleinberg, J., Mullainathan, S., & Raghavan, M. (2017) · Schloss Dagstuhl – Leibniz-Zentrum für Informatik · doi:10.4230/lipics.itcs.2017.43 · Cited by 943
Research works printed but not linked: 4
- Kohavi, R. Scaling up the accuracy of naive-Bayes classifiers: a decision-tree hybrid. In Proceedings of the Second International Conference on Knowledge Discovery and Data Mining , 1996. URL https://archive. ics.uci.edu/ml/datasets/adult .
- Kusner, M. J., Loftus, J. R., Russell, C., and Silva, R. Counterfactual fairness. In NIPS , 2017.
- bellamy, 2018, AI Fairness 360: An extensible toolkit for detecting, understanding, and mitigating unwanted algorithmic bias, arXiv 1810 01943
- Narayanan, A. Translation tutorial: 21 fairness definitions and their politics. In Conference on Fairness, Accountability, and Transparency , February 2018.
Cited by
Items 1,001–1,009 of 1,009
Predicting Worker Accuracy from Nonverbal Behaviour: Benefits and Potential for Algorithmic Bias
Toyoda, Y., Lucas, G., & Gratch, J. S. (2021) · Companion Publication of the International Conference on Multimodal Interaction (ICMI Companion) · doi:10.1145/3461615.3485427 · Cited by 6
Trustworthy Machine Learning for Cloud-Based Internet of Things (IoT)
Yadav, S., Joshi, R. C., & Yadav, D. (2022) · Springer eBooks · doi:10.1007/978-3-030-86749-2_9 · Cited by 5
Debiasing Neural Retrieval via In-batch Balancing Regularization
Li, Y., Wei, X., Wang, Z., Wang, S., Bhatia, P., Ma, X., & Arnold, A. (2022) · Workshop on Gender Bias in Natural Language Processing (GeBNLP) · doi:10.18653/v1/2022.gebnlp-1.5 · Cited by 10
Fairkit-learn: A Fairness Evaluation and Comparison Toolkit
Johnson, B., & Brun, Y. (2022) · ACM/IEEE International Conference on Software Engineering: Companion Proceedings (ICSE-Companion) · doi:10.1109/icse-companion55297.2022.9793775 · Cited by 5
A Pragmatic Framework for Federated Learning Risk and Governance in Academic Medical Centers
Bottomly, D., Barnes, B., Mavuwa, K., Lee, N., Roth, H. R., Chen, C., & McWeeney, S. K. (2026) · JMIR AI · doi:10.2196/80022 · Cited by 6
“Are there any detectable issues with fairness or bias against certain groups, which can be quantified using several toolkits [18-20]?”
Constantin, R., Duck, M., Alexandrov, A., Matosevic, P., Keidar, D., & El-Assady, M. (2022) · 2022 IEEE Workshop on TRust and EXpertise in Visual Analytics (TREX) · doi:10.1109/trex57753.2022.00005 · Cited by 3
Taka, E., Nakao, Y., Sonoda, R., Yokota, T., Luo, L., & Stumpf, S. (2023) · arXiv · doi:10.48550/arxiv.2312.08064
“Many toolkits have been developed to facilitate evaluating and mitigating bias, for example, AI Fairness 360 [7], Fairlearn [77], and the What-If Tool [78].”
BackgroundInfluentialAuditing a Dutch Public Sector Risk Profiling Algorithm Using an Unsupervised Bias Detection Tool
Holstege, F., Jorgensen, M., Padh, K., Parie, J., Proroković, K., Persson, J., & Snoek, L. (2025) · arXiv · doi:10.48550/arxiv.2502.01713
“Most bias detection methods assume access to demographic groups (Elliot et al., 2009; Hardt et al., 2016; Kusner et al., 2017; Kleinberg et al., 2018; Bellamy et al., 2019; Delaney et al., 2024).”
Principles to Practices for Responsible AI: Closing the Gap
Schiff, D., Rakova, B., Ayesh, A., Fanti, A., & Lennon, M. (2020) · arXiv · doi:10.48550/arxiv.2006.04707
Metadata
- Authors
- Bellamy, R. K. E., Dey, K., Hind, M., Hoffman, S. C., Houde, S., Kannan, K., Lohia, P., Martino, J., Mehta, S., Mojsilović, A., Nagar, S., Ramamurthy, K. N., Richards, J., Saha, D., Sattigeri, P., Singh, M., Varshney, K. R., & Zhang, Y.
- ORCID
- Venue
- IBM Journal of Research and Development
- Publisher
- IBM
- Published
- 2019-07-01
- Volume
- 63
- Issue
- 4/5
- Pages
- 4:1-4:15
- ISSN
- 0018-8646 (ISSN-L)
- OpenAlex
- W2974817986
- Cited by
- 884
- References
- 31
- Citations by year
- 2026: 163 · 2025: 226 · 2024: 145 · 2023: 143 · 2022: 99 · 2021: 69 · 2020: 35 · 2019: 4
- FWCI
- 90.90
- Type
- journal article
- Language
- en
- Open access
- closed
- Locations
- IBM Journal of Research and Development (publishedVersion)
- Topics
- Physical Sciences › Computer Science › Artificial Intelligence › Ethics and Social Impacts of AI
- Physical Sciences › Computer Science › Artificial Intelligence › Explainable Artificial Intelligence (XAI)
- Physical Sciences › Computer Science › Artificial Intelligence › Imbalanced Data Classification Techniques
- Keywords
- algorithmic fairness, algorithmic bias detection, bias mitigation, fairness metrics, open-source software toolkit, high-stakes decision making
About these checks
Registry, retraction, Cites and statistics results are computed, not judged, with one exception: a printed reference that no index lists is read once by a model before it counts as a citation error. Claims are extracted by a model and kept only when their quote appears verbatim in the text; each cited source is then checked, with a model’s help, for whether it says what the claim relies on. Those verdicts can be wrong — read the claim’s quote and the cited source before relying on one.
Statistics and arithmetic are recomputed, not judged.
Confidence bands are shown only for fields calibrated on our annotated test set. None is calibrated yet, so no band is shown.
What counts as a claim ›How we measure confidence ›How we check this ›
Are you an author, or do you see a problem with this page? Request a review
Data sources
Bibliographic data: Semantic Scholar, OpenAlex, Crossref.
Contains information from the Semantic Scholar Academic Graph Datasets, made available under the ODC Attribution License (ODC-BY 1.0).
Semantic Scholar’s data is described in: Kinney, R., et al. (2023). The Semantic Scholar Open Data Platform. arXiv:2301.10140.