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 901–1,000 of 1,009
Towards Responsible AI in Education: Hybrid Recommendation System for K-12 Students Case Study
Drushchak, N., Tyshchenko, V., & Polyakovska, N. (2025) · doi:10.1109/raie66699.2025.00015 · Cited by 11
FairZK: A Scalable System to Prove Machine Learning Fairness in Zero-Knowledge
Zhang, T., Dong, S., Kose, O. D., Shen, Y., & Zhang, Y. (2025) · IEEE Symposium on Security and Privacy (S&P) · doi:10.1109/sp61157.2025.00205 · Cited by 13
“Several tools have been developed in recent years to test the fairness of ML models, such as [4], [9], [13], [41], [49], [62], [64].”
Self-citationPathak, S., Kaakandikar, R. M., & Nim, D. (2025) · Advances in computational intelligence and robotics book series · doi:10.4018/979-8-3693-9611-7.ch010 · Cited by 6
AI-driven active sourcing in recruitment: addressing contestability in automated hiring systems
Hadžić, B., Brandner, L. T., Weber, T., & Rätsch, M. (2025) · Frontiers in Computer Science · doi:10.3389/fcomp.2025.1629522 · Cited by 8
PCIV method for Indirect Bias Quantification in AI and ML Models
Garg, A., & Rajesh, S. L. (2021) · International Journal of Scientific Research in Computer Science Engineering and Information Technology · doi:10.32628/cseit217251 · Cited by 7
Trusted artificial intelligence: Strengthening digital protection
Avdoshin, S. M., & Pesotskaya, E. (2022) · Бизнес-информатика · doi:10.17323/2587-814x.2022.2.62.73 · Cited by 7
Sarkar, P., & Liem, C. C. S. (2024) · Proceedings of the ACM on Human-Computer Interaction · doi:10.1145/3637360 · Cited by 7
FairHash: A Fair and Memory/Time-efficient Hashmap
Shahbazi, N., Sintos, S., & Asudeh, A. (2024) · Proceedings of the ACM on Management of Data · doi:10.1145/3654939 · Cited by 9
AIM: Attributing, Interpreting, Mitigating Data Unfairness
Liu, Z., Qiu, R., Zeng, Z., Zhu, Y., Hamann, H. F., & Tong, H. (2024) · ACM SIGKDD Conference on Knowledge Discovery and Data Mining (KDD) · doi:10.1145/3637528.3671797 · Cited by 17
“This further validates the effectiveness and generality of AIM in mitigating unfairness.”
Bringing practical statistical science to AI and predictive model fairness testing
Lo, V. S. Y., Datta, S., & Salami, Y. (2024) · AI and Ethics · doi:10.1007/s43681-024-00518-2 · Cited by 10
Using Self-supervised Learning Can Improve Model Fairness
Yfantidou, S., Spathis, D., Constantinides, M., Vakali, A. I., Quercia, D., & Kawsar, F. (2024) · ACM SIGKDD Conference on Knowledge Discovery and Data Mining (KDD) · doi:10.1145/3637528.3671991 · Cited by 12
“For example, for the disparate impact ratio (DIR) metric: The ideal deviation lies close to 0.0 (i.e., no deviation from parity), whereas values below 0.2 fall within the acceptable (“fair”) range [2].”
BackgroundInfluentialWatson, M., Chambers, P., Steventon, L., King, J. H., Ercia, A., Shaw, H. M., & Moubayed, N. A. (2024) · BMJ Oncology · doi:10.1136/bmjonc-2024-000430 · Cited by 7
Reducing bias in healthcare artificial intelligence: A white paper
Sun, C., & Harris, S. L. (2024) · Health Informatics Journal · doi:10.1177/14604582241291410 · Cited by 7
GNNFairViz: Visual Analysis for Graph Neural Network Fairness
Ye, X., Feng, J., Purificato, E., Boratto, L., Kamp, M., Huang, Z., & Chen, S. (2025) · IEEE Transactions on Visualization and Computer Graphics · doi:10.1109/tvcg.2025.3542419 · Cited by 7
Talwar, A., Turner, S., Maw, C., Quayle, G., Watt, T. N., Gohil, S., Duckworth, E., & Ciurtin, C. (2025) · BMJ Open · doi:10.1136/bmjopen-2024-086117 · Cited by 6
Looking Ahead: Incorporating AI in MLIS Competencies
Ghosh, S., & McCoy, D. (2024) · School of Information Student Research Journal · doi:10.55917/2575-2499.1535 · Cited by 6
Performance Evaluation for Detecting and Alleviating Biases in Predictive Machine Learning Models
Khakurel, U. B., Abdelmoumin, G., & Rawat, D. B. (2025) · ACM transactions on probabilistic machine learning. · doi:10.1145/3729432 · Cited by 6
AI and Diversity: Ensuring Fairness in Automated Decision-Making
Subrahmanyam, S., & Baz, B. E. (2025) · Advances in computational intelligence and robotics book series · doi:10.4018/979-8-3373-3104-1.ch002 · Cited by 6
Evaluating Neural Model Robustness for Machine Comprehension
Wu, W. M. C., Arendt, D., & Volkova, S. (2021) · Conference of the European Chapter of the Association for Computational Linguistics · doi:10.18653/v1/2021.eacl-main.210 · Cited by 9
Performance analysis of machine learning algorithms trained on biased data
Broder, R. S., & Berton, L. (2021) · doi:10.5753/eniac.2021.18283 · Cited by 6
He, F., Wu, X., Zhang, W., & Huang, X. (2023) · Connection Science · doi:10.1080/09540091.2023.2184310 · Cited by 7
“Because accuracy and average odds difference (AOD; Bellamy et al., 2019) are the most commonly used indicators, they are evaluated in selecting the competent base classifiers.”
BackgroundMethodInfluentialA Review of Partial Information Decomposition in Algorithmic Fairness and Explainability
Dutta, S., & Hamman, F. (2023) · Entropy · doi:10.3390/e25050795 · Cited by 14
“There are several ways to incorporate statistical parity [51], such as minimizing the absolute gap |Pr (Ŷ|Z = 1)− Pr (Ŷ|Z = 0)| either during pre-processing, training, or postprocessing.”
BackgroundMethodInfluentialCertifying Fairness of Probabilistic Circuits
Selvam, N. R., den Broeck, G. V., & Choi, Y. (2023) · Proceedings of the AAAI Conference on Artificial Intelligence · doi:10.1609/aaai.v37i10.26447 · Cited by 10
Benchmarking the Effect of Poisoning Defenses on the Security and Bias of Deep Learning Models
Baracaldo, N., Ahmed, F., Eykholt, K., Zhou, Y., Priya, S., Lee, T., Kadhe, S., Tan, M., Polavaram, S., Suggs, S., et al. (2023) · IEEE Security and Privacy Workshops (SPW) · doi:10.1109/spw59333.2023.00010 · Cited by 8
“These groups are typically based on sensitive attributes such as race, gender, and age [21], [22].”
BackgroundOn Adversarial Robustness of Demographic Fairness in Face Attribute Recognition
Zeng, H., Yue, Z., Shang, L., Zhang, Y., & Wang, D. (2023) · International Joint Conference on Artificial Intelligence · doi:10.24963/ijcai.2023/59 · Cited by 6
Self-citationUnmasking the Shadows: Exploring Unethical AI Implementation
Dwivedi, D. N., & Mahanty, G. (2024) · Advances in human resources management and organizational development book series · doi:10.4018/979-8-3693-0724-3.ch012 · Cited by 7
Ahn, E., Tejeda, Y., & Yang, Y. (2024) · Family Relations · doi:10.1111/fare.13114 · Cited by 7
Fairness Artificial Intelligence in Clinical Decision Support: Mitigating Effect of Health Disparity
Wu, H., Zhu, Y., Shi, W., Li, T., & Wang, M. D. (2024) · IEEE Journal of Biomedical and Health Informatics · doi:10.1109/jbhi.2024.3513398 · Cited by 9
Bias Mitigation Methods: Applicability, Legality, and Recommendations for Development
Waller, M., Rodrigues, O., Lee, M. S. A., & Cocarascu, O. (2024) · Journal of Artificial Intelligence Research · doi:10.1613/jair.1.16759 · Cited by 11
Generative Artificial Intelligence and Assessment of Learning: Challenges and Perspectives
Kaddouri, M., Mhamdi, K., Jabri, A., Boukare, M., & Jmad, S. (2025) · Advances in educational technologies and instructional design book series · doi:10.4018/979-8-3693-6527-4.ch010 · Cited by 7
Agbadamasi, T. O., Opoku, L. K., Adukpo, T. K., & Mensah, N. (2025) · World Journal of Advanced Research and Reviews · doi:10.30574/wjarr.2025.25.3.0814 · Cited by 13
How robust is your fair model? Exploring the robustness of prominent fairness strategies
Small, E. A., Shao, W., Zhang, Z., Liu, P., Chan, J., Sokol, K., & Salim, F. D. (2025) · Data Mining and Knowledge Discovery · doi:10.1007/s10618-025-01112-8 · Cited by 8
Evaluation of Bias in Sensitive Personal Information Used to Train Financial Models
Bryant, R., Cintas, C., Wambugu, I. W., Kinai, A., Diriye, A., & Weldemariam, K. (2019) · IEEE Global Conference on Signal and Information Processing · doi:10.1109/globalsip45357.2019.8969527 · Cited by 6
Identifying and addressing unintended values when designing (with) Artificial Intelligence
Stoimenova, N., & Kleinsmann, M. S. (2020) · Proceedings of DRS · doi:10.21606/drs.2020.222 · Cited by 6
Fairness of Machine Learning in Search Engines
Fang, Y., Liu, H., Tao, Z., & Yurochkin, M. (2022) · ACM International Conference on Information and Knowledge Management (CIKM) · doi:10.1145/3511808.3557501 · Cited by 9
Comparing the Robustness of Classical and Deep Learning Techniques for Text Classification
Tran, Q., Shpileuskaya, K., Zaunseder, E., Putzar, L., & Blankenburg, S. (2022) · IEEE International Joint Conference on Neural Network · doi:10.1109/ijcnn55064.2022.9892242 · Cited by 11
Mythical Ethical Principles for AI and How to Attain Them
Slavkovik, M. (2023) · Lecture notes in computer science · doi:10.1007/978-3-031-24349-3_15 · Cited by 6
Formal Group Fairness and Accuracy in Automated Decision Making
Langenberg, A., Ma, S.-C., Ermakova, T., & Fabian, B. (2023) · Mathematics · doi:10.3390/math11081771 · Cited by 8
Mitigando Vieses no Aprendizado de Máquina
Ruback, L., Carvalho, D., & Avila, S. (2022) · iSys - Brazilian Journal of Information Systems · doi:10.5753/isys.2022.2396 · Cited by 12
VerifyML: Obliviously Checking Model Fairness Resilient to Malicious Model Holder
Xu, G., Han, X., Deng, G., Zhang, T., Xu, S., Ning, J., Yang, A., & Li, H. (2023) · IEEE Transactions on Dependable and Secure Computing · doi:10.1109/tdsc.2023.3290562 · Cited by 6
Revisiting Lightweight Compiler Provenance Recovery on ARM Binaries
Kim, J. Z., Genkin, D., & Leach, K. (2023) · IEEE International Conference on Program Comprehension (ICPC) · doi:10.1109/icpc58990.2023.00044 · Cited by 9
“A fast model is beneficial not only for efficiency, but also for explainability: iteratively excluding subsets of training data and retraining can help developers understand the contribution of removed subsets to the model’s behavior, and check for biases [1, 30, 40].”
BackgroundDiversity in issue assignment: humans vs bots
Murali, A., Sahu, G., Thangarajah, K., Zimmerman, B. D., Rodríguez-Pérez, G., & Nagappan, M. (2024) · Empirical Software Engineering · doi:10.1007/s10664-023-10424-6 · Cited by 6
Addressing diversity in hiring procedures: a generative adversarial network approach
Marra, T., & Kubiak, E. (2024) · AI and Ethics · doi:10.1007/s43681-024-00445-2 · Cited by 8
“This shift, amplified by the capabilities of machine learning, hints at the evolving landscape of fairness interventions, where biases can be addressed effectively even after model training [e.g. , 11].”
The Need for User-centred Assessment of AI Fairness and Correctness
Stumpf, S., Taka, E., Nakao, Y., Luo, L. K., Sonoda, R., & Yokota, T. (2024) · ACM Conference on User Modeling, Adaptation and Personalization (UMAP) · doi:10.1145/3631700.3664912 · Cited by 8
“To date, a number of tools have been developed to help AI experts assess and mitigate bias and unfairness while maintaining accuracy [1, 2, 5, 16].”
A Maximal Correlation Approach to Imposing Fairness in Machine Learning
Lee, J. A., Bu, Y., Sattigeri, P., Panda, R., Wornell, G. W., Karlinsky, L., & Feris, R. S. (2022) · IEEE International Conference on Acoustics Speech and Signal Processing · doi:10.1109/icassp43922.2022.9747263 · Cited by 16
Self-citationJudicial Artificial Intelligence Bias: A Survey and Recommendations
Ngige, O. C., Awodele, O., & Balogun, O. (2021) · Transactions on Machine Learning and Artificial Intelligence · doi:10.14738/tmlai.92.10118 · Cited by 7
Behavioral Phenotyping for Predictive Model Equity and Interpretability in STEM Education
Tyler, M., Liu, A. X., & Srinivasan, R. (2021) · Lecture notes in computer science · doi:10.1007/978-3-030-78270-2_64 · Cited by 6
Identifying Bias in Data Using Two-Distribution Hypothesis Tests
Yik, W., Serafini, L., Lindsey, T., & Montañez, G. D. (2022) · Proceedings of the AAAI/ACM Conference on AI Ethics and Society · doi:10.1145/3514094.3534169 · Cited by 9
VIsCUIT: Visual Auditor for Bias in CNN Image Classifier
Lee, S., Hoffman, J., Wang, Z. J., & Chau, D. H. (2022) · IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings - IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings · doi:10.1109/cvpr52688.2022.02081 · Cited by 14
Mitigating Representation Bias in Action Recognition: Algorithms and Benchmarks
Duan, H., Zhao, Y., Chen, K., Xiong, Y., & Lin, D. (2023) · Lecture notes in computer science · doi:10.1007/978-3-031-25069-9_36 · Cited by 10
Do's and Don'ts for Human and Digital Worker IntegrationPreprint
Muthusamy, V., Unuvar, M., Völzer, H., & Weisz, J. D. (2020) · arXiv (Cornell University) · doi:10.48550/arxiv.2010.07738 · Cited by 9
Selective Regression Under Fairness CriteriaPreprint
Shah, A., Bu, Y., Lee, J. K.-W., Das, S., Panda, R., Sattigeri, P., & Wornell, G. W. (2021) · arXiv (Cornell University) · doi:10.48550/arxiv.2110.15403 · Cited by 10
Self-citationDownstream Fairness Caveats with Synthetic Healthcare DataPreprint
Bhanot, K., Baldini, I., Wei, D., Zeng, J., & Bennett, K. P. (2022) · arXiv (Cornell University) · doi:10.48550/arxiv.2203.04462 · Cited by 8
Mitigating Bias in Algorithmic Systems - A Fish-Eye View
Orphanou, K., Otterbacher, J., Kleanthous, S., Batsuren, K., Giunchiglia, F., Bogina, V., Tal, A. S., Hartman, A., & Kuflik, T. (2021) · Zenodo (CERN European Organization for Nuclear Research) · doi:10.5281/zenodo.6240582 · Cited by 6
fairml: A Statistician's Take on Fair Machine Learning ModellingPreprint
Scutari, M. (2023) · arXiv (Cornell University) · doi:10.48550/arxiv.2305.02009 · Cited by 6
Shedding light on underrepresentation and Sampling Bias in machine learningPreprint
Zhioua, S., & Binkytė, R. (2023) · arXiv (Cornell University) · doi:10.48550/arxiv.2306.05068 · Cited by 6
“(6)We use the same dataset versions and learning algorithms parameters as IBM AIF360 [2]”
MethodA Suite of Fairness Datasets for Tabular ClassificationPreprint
Hirzel, M. J., & Feffer, M. (2023) · arXiv (Cornell University) · doi:10.48550/arxiv.2308.00133 · Cited by 6
Data Augmentation for Personal Knowledge Base PopulationPreprint
Vannur, L. S., Ganesan, B., Nagalapatti, L., Patel, H., & Thippeswamy, M. N. (2020) · arXiv (Cornell University) · doi:10.48550/arxiv.2002.10943 · Cited by 10
Explainable AI for Financial Risk Management
Bowden, J., Cummins, M., Dao, D., & Jain, K. (2024) · Strathprints: The University of Strathclyde institutional repository (University of Strathclyde) · doi:10.17868/strath.00089573 · Cited by 15
Raza, S., Qureshi, R., Zahid, A., Muneer, A., Zafar, A., Kamawal, S., Sadak, F., Fioresi, J., Saeed, M., Sapkota, R., et al. (2025) · arXiv · doi:10.48550/arxiv.2502.08650 · Cited by 5
“• IBM AI Fairness 360 (AIF360) [22]: .”
A Taxonomy of Machine Learning Fairness Tool Specifications, Features and Workflows
Mim, S. A., Smith, J., & Johnson, B. (2023) · IEEE Symposium on Visual Languages and Human-Centric Computing (VL/HCC) · doi:10.1109/vl-hcc57772.2023.00036 · Cited by 8
“2) Evaluation Parameter: Given there are over 70 existing fairness metrics [4], we grouped metrics by high-level categories.”
MethodInteractive Counterfactual Exploration of Algorithmic Harms in Recommender Systems
Ahn, Y., Wolter, Q. K., Dick, J., Dick, J., & Lin, Y.-R. (2024) · IEEE Visualization in Data Science (VDS) · doi:10.1109/vds63897.2024.00009 · Cited by 7
Modular oversight methodology: a framework to aid ethical alignment of algorithmic creations
Kyriakou, K., & Otterbacher, J. (2024) · Design Science · doi:10.1017/dsj.2024.23 · Cited by 6
“…and testing of algorithmic systems consists of a wide collection of tools, methods and frameworks for developers to assess their creations (e.g. AI Fairness 360 (Bellamy et al. 2019), Aequitas (Saleiro et al. 2018)), it is critical to examine their applicability to intelligent systemsbasedonAI.”
Fairness Challenges in the Design of Machine Learning Applications for Healthcare
Ryan, S., Cai, W., Bowman, R., & Doherty, G. J. (2025) · ACM Transactions on Computing for Healthcare · doi:10.1145/3728368 · Cited by 9
“There currently exist approaches to incorporating fairness in the design process, such as the use of software tools for the auditing and assessment of ML models during development [4] and organisational management tools [31].”
Enhancing Explainability, Robustness, and Autonomy: A Comprehensive Approach in Trustworthy AI
Ahmed, M. U., Begum, S., Barua, S., Masud, A. N., Flumeri, G. D., & Navarin, N. (2025) · IEEE Symposium on Trustworthy, Explainable and Responsible Computational Intelligence (CITREx) · doi:10.1109/citrex64975.2025.10974944 · Cited by 9
“AIF360 is an open-source toolkit developed by IBM that includes over 70 fairness metrics and 11 bias mitigation algorithms, making it a powerful tool for bias monitoring and mitigation [16].”
Chen, G., & Yang, Z. (2025) · Frontiers in Physiology · doi:10.3389/fphys.2025.1630807 · Cited by 5
Wu, M., Zhao, Y., Han, S., Liu, M. X., & Shen, H. Y. (2026) · Proceedings of the ACM on Human-Computer Interaction · doi:10.1145/3816897 · Cited by 6
Guerdan, L., Saxena, D., Chancellor, S., Wu, Z. S., & Holstein, K. (2025) · Proceedings of the ACM on Human-Computer Interaction · doi:10.1145/3757628 · Cited by 6
“Yet existing model training and evaluation toolkits often assume that datasets are fixed [12, 21, 146].”
Explainable AI (XAI) in Healthcare: Building Trust in Medical Diagnosis Systems
Khade, M. P. S. (2025) · International Journal of Scientific Research in Science and Technology · doi:10.32628/ijsrst25126288 · Cited by 5
Revisiting Pre-processing Group Fairness: A Modular Benchmarking Framework
Oldfield, B., Xu, Z., & Kandanaarachchi, S. (2025) · ACM International Conference on Information and Knowledge Management (CIKM) · doi:10.1145/3746252.3761650 · Cited by 6
Parsoya, R., Bisht, B., Vlaskin, M. S., Jaiswal, K. K., Chauhan, P. K., Tripathi, M. K., KURBATOVA, A. I., Rajput, V. S., & Kumar, V. (2025) · Cleaner Water · doi:10.1016/j.clwat.2025.100189 · Cited by 7
Ding, S., & Magerko, B. S. (2026) · ACM Technical Symposium on Computer Science Education (SIGCSE) · doi:10.1145/3770761.3777259 · Cited by 7
“GenAI systems should make their processes and outputs understandable, ensuring algorithmic transparency to users [2, 19, 23].”
Zhong, J., Al‐Zaiti, S. S., Bennett, D., Do, S., Gaudino, M. F. L., Gichoya, J. W., Musaad, S. M. A., Narayan, S. M., Sajobi, T. T., Yu, S., et al. (2026) · Circulation Genomic and Precision Medicine · doi:10.1161/hcg.0000000000000101 · Cited by 5
Yapay Zekâ Risklerinin Etik Yönünden Değerlendirilmesi
Efe, A. (2021) · Bilgi ve İletişim Teknolojileri Dergisi · Cited by 27
Introduction to Machine Learning for Physicians: A Survival Guide for Data Deluge
Vogt, J. E., Özkan, E., & Marcinkevičs, R. (2023) · doi:10.1201/9781003386070-2 · Cited by 5
Shrestha, H., Cachel, K., Alkhathlan, M., Rundensteiner, E. A., & Harrison, L. (2023) · ACM Conference on Fairness, Accountability, and Transparency (FAccT) · doi:10.1145/3593013.3594108 · Cited by 8
Shih, J., & Chin, Z.-H. (2023) · IEEE International Conference on Electronic Communications, Internet of Things and Big Data (ICEIB) · doi:10.1109/iceib57887.2023.10170339 · Cited by 5
“Therefore, previous studies proposed several bias evaluation metrics along with bias mitigation algorithms to counter the unfairness issue of machine learning models [11].”
BackgroundSchlagowski, R., Volanti, M., Weitz, K., Mertes, S., Kuch, J. M., & André, E. (2024) · Frontiers in Virtual Reality · doi:10.3389/frvir.2024.1340250 · Cited by 7
Ethnic representation within virtual reality: a co-design study in a forensic youth care setting
Schaarsberg, R. E. K., van Dam, L., Widdershoven, G. A. M., Lindauer, R., & Popma, A. (2024) · BMC Digital Health · doi:10.1186/s44247-024-00081-0 · Cited by 6
“Although primarily focusing on algorithmic bias, tools for detecting and mitigating bias are available (e.g., [42]).”
Towards Generalised and Incremental Bias Mitigation in Personality Computing
Jiang, J., Manoranjan, V., Salam, H., & Çeliktutan, O. (2024) · IEEE Transactions on Affective Computing · doi:10.1109/taffc.2024.3409830 · Cited by 8
“Disparate Impact (a.k.a, adverse impact) Ratio (DIR) [64] and Statistical Parity Difference (SPD) [66] are used to measure the deviation of the Statistical Parity.”
Fairness testing for uplift models
Lo, V. S. Y., Xu, Y., Li, Z., & Thielbar, M. (2024) · Journal of Marketing Analytics · doi:10.1057/s41270-024-00339-6 · Cited by 5
Analyzing Fairness of Computer Vision and Natural Language Processing Models
Rashed, A., Kallich, A., & Eltayeb, M. M. (2025) · Information · doi:10.3390/info16030182 · Cited by 7
Efosa-Zuwa, E., Oladipupo, O. O., & Oyelade, J. O. (2025) · Statistics Optimization & Information Computing · doi:10.19139/soic-2310-5070-2398 · Cited by 6
“Incorporating bias assessments into training and into each run, we can identify and remedy the errors before these models reach customers’ hands, delivering models that work and are fairer respectively [133] [134].”
A Framework for Integrating AI-Powered Systems to Mitigate Bias Risk in HRMFunctions
Naoum, R. (2025) · Marketing & Menedzsment · doi:10.15170/mm.2025.59.02.05 · Cited by 7
Ahmad, M. A., Eckert, C., Allen, C. M. B., Kumar, V., Hu, J., & Teredesai, A. M. (2021) · IEEE International Conference on Healthcare Informatics (ICHI) · doi:10.1109/ichi52183.2021.00104 · Cited by 5
A Tool Bundle for AI Fairness in Practice
Ruf, B., & Detyniecki, M. (2022) · CHI Conference Extended Abstracts on Human Factors in Computing Systems (CHI EA) · doi:10.1145/3491101.3519878 · Cited by 7
Recover Fair Deep Classification Models via Altering Pre-trained Structure
Zhang, Y., Gao, S., & Huang, H. (2022) · Lecture notes in computer science · doi:10.1007/978-3-031-19778-9_28 · Cited by 8
Self-citationThe Need for an Enhanced Process Methodology for Ethical Data Science Projects
Lahiri, S., & Saltz, J. (2023) · IEEE International Symposium on Ethics in Engineering, Science, and Technology (ETHICS) · doi:10.1109/ethics57328.2023.10155007 · Cited by 5
FairSwiRL: fair semi-supervised classification with representation learning
Yang, S., Cerrato, M., Ienco, D., Pensa, R. G., & Esposito, R. (2023) · Machine Learning · doi:10.1007/s10994-023-06342-9 · Cited by 5
Biu, P. W., Oliha, J. S., & Obi, O. C. (2024) · GSC Advanced Research and Reviews · doi:10.30574/gscarr.2024.18.2.0058 · Cited by 6
Exploring Visualization for Fairness in AI Education
Yan, X., Zhou, Y., Mishra, A., Mishra, H., & Wang, B. (2024) · IEEE Pacific Visualization Conference (PacificVis) · doi:10.1109/pacificvis60374.2024.00010 · Cited by 5
“These metrics are also featured in AEquitas [44] and AI Fairness 360 [5].”
BackgroundMethodInfluentialA Clearer View on Fairness: Visual and Formal Representations for Comparative Analysis
Mendez, J., Kampik, T., Tubella, A. A., & Dignum, V. (2024) · Linköping electronic conference proceedings · doi:10.3384/ecp208013 · Cited by 6
“Still, tools for operationalizing fairness, such as IBM’s AI Fairness 360 [4], Google’s What-if tool [39], and Microsoft’s Fairlearn [7], depend on these highly specific statistical for-malizations that reflect group or individual fairness notions.”
MethodPredicting Fairness of ML Software Configurations
Robles, S., Monjezi, V., Крейнович, В., Trivedi, A., & Tizpaz-Niari, S. (2024) · doi:10.1145/3663533.3664040 · Cited by 5
“Similarly, average odd difference (AOD) is the average of differences between the true positive rates (TPR) and the false positive rates (FPR) of two protected groups [3, 8, 40, 45].”
BackgroundFarayola, M. M., Bendechache, M., Saber, T., Connolly, R., & Tal, I. (2024) · International Conference on Availability, Reliability and Security (ARES) · doi:10.1145/3664476.3669978 · Cited by 9
“• Disparate Impact Remover (DIR): Disparate Impact re-mover is a pre-processing method that improves group fairness by altering feature values related to sensitive attributes without affecting rank ordering within groups and thereby targeting the fairness metric such as the disparate impact [5, 22].”
InfluentialStrotherm, J., Müller, A., Hammer, B., & Paaßen, B. (2024) · Springer eBooks · doi:10.1007/978-3-658-43816-6_9 · Cited by 7
“Zwei Bei-spiele dafür sind Aequitas von Saleiro et al. (2019) und AI Fairness 360 von Bellamy et al. (2019).”
BackgroundPatra ModelCards: AI/ML Accountability in the Edge-Cloud Continuum
Withana, S., & Plale, B. (2024) · IEEE International Conference on eScience · doi:10.1109/e-science62913.2024.10678710 · Cited by 6
“The Fairlearn [6] library emerged as the most suitable fairness tool among other tools such as AI Fairness 360 [5] and Aequitas [31].”
MethodGonzález-Sendino, R., Serrano, E., & Bajo, J. (2025) · Engineering Applications of Artificial Intelligence · doi:10.1016/j.engappai.2024.109979 · Cited by 6
Konertz, R., & Schönhof, R. (2020) · Nomos Verlagsgesellschaft mbH & Co. KG eBooks · doi:10.5771/9783748910503 · Cited by 5
A Reliability-aware Distributed Framework to Schedule Residential Charging of Electric Vehicles
Meyur, R., Thorve, S., MARATHE, M. V., Vullikanti, A. K. S., Swarup, S., & Mortveit, H. (2022) · International Joint Conference on Artificial Intelligence · doi:10.24963/ijcai.2022/710 · Cited by 5
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.