Computer Science · Literature

Research papers on Algorithmic bias and fairness

Recent and highly-cited academic work on algorithmic bias and fairness, gathered from Semantic Scholar, CrossRef and OpenAlex.

1. Greedy function approximation: A gradient boosting machine.

   Jerome H. Friedman · 2001 · The Annals of Statistics · 29,332 citations

   Function estimation/approximation is viewed from the perspective of numerical optimization in function space, rather than parameter space. A connection is made between stagewise additive expansions and steepest-descent minimization. A general gradient descent “boosting” paradigm is developed for additive expansions based on any fitting criterion.Specific algorithms are presented for least-squares, least absolute deviation, and Huber-M loss functions for regression, and multiclass logistic likelihood for classification. Special enhancements are derived for the particular case where the individual additive components are regression trees, and tools for interpreting such “TreeBoost” models are

2. Deep Reinforcement Learning with Double Q-Learning

   Hado van Hasselt, Arthur Guez, David Silver · 2016 · 6,092 citations

   The popular Q-learning algorithm is known to overestimate action values under certain conditions. It was not previously known whether, in practice, such overestimations are common, whether they harm performance, and whether they can generally be prevented. In this paper, we answer all these questions affirmatively. In particular, we first show that the recent DQN algorithm, which combines Q-learning with a deep neural network, suffers from substantial overestimations in some games in the Atari 2600 domain. We then show that the idea behind the Double Q-learning algorithm, which was introduced in a tabular setting, can be generalized to work with large-scale function approximation. We propose

3. Machine Learning Interpretability: A Survey on Methods and Metrics

   Diogo V. Carvalho, Eduardo M. Pereira, Jaime S. Cardoso · 2019 · Electronics · 1,781 citations

   Machine learning systems are becoming increasingly ubiquitous. These systems’s adoption has been expanding, accelerating the shift towards a more algorithmic society, meaning that algorithmically informed decisions have greater potential for significant social impact. However, most of these accurate decision support systems remain complex black boxes, meaning their internal logic and inner workings are hidden to the user and even experts cannot fully understand the rationale behind their predictions. Moreover, new regulations and highly regulated domains have made the audit and verifiability of decisions mandatory, increasing the demand for the ability to question, understand, and trust mach

4. Kernel methods in machine learning

   Thomas Hofmann, Bernhard Schölkopf, Alexander J. Smola · 2008 · The Annals of Statistics · 1,603 citations

   We review machine learning methods employing positive definite kernels. These methods formulate learning and estimation problems in a reproducing kernel Hilbert space (RKHS) of functions defined on the data domain, expanded in terms of a kernel. Working in linear spaces of function has the benefit of facilitating the construction and analysis of learning algorithms while at the same time allowing large classes of functions. The latter include nonlinear functions as well as functions defined on nonvectorial data. We cover a wide range of methods, ranging from binary classifiers to sophisticated methods for estimation with structured data.

5. AI Fairness 360: An extensible toolkit for detecting and mitigating algorithmic bias

   Rachel Bellamy, Kuntal Dey, Michael Hind, et al. · 2019 · IBM Journal of Research and Development · 822 citations

   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 ( <uri xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">https://github.com/ibm/aif360</uri> ). 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 alg

6. Algorithmic Bias in Education

   Ryan S. Baker, Aaron Hawn · 2021 · International Journal of Artificial Intelligence in Education · 660 citations

   In this paper, we review algorithmic bias in education, discussing the causes of that bias and reviewing the empirical literature on the specific ways that algorithmic bias is known to have manifested in education. While other recent work has reviewed mathematical definitions of fairness and expanded algorithmic approaches to reducing bias, our review focuses instead on solidifying the current understanding of the concrete impacts of algorithmic bias in education—which groups are known to be impacted and which stages and agents in the development and deployment of educational algorithms are implicated. We discuss theoretical and formal perspectives on algorithmic bias, connect those perspect

7. Algorithmic fairness in artificial intelligence for medicine and healthcare

   Richard J. Chen, Judy J. Wang, Drew F. K. Williamson, et al. · 2023 · Nature Biomedical Engineering · 629 citations

8. A Review on Fairness in Machine Learning

   Dana Pessach, Erez Shmueli · 2022 · ACM Computing Surveys · 551 citations

   An increasing number of decisions regarding the daily lives of human beings are being controlled by artificial intelligence and machine learning (ML) algorithms in spheres ranging from healthcare, transportation, and education to college admissions, recruitment, provision of loans, and many more realms. Since they now touch on many aspects of our lives, it is crucial to develop ML algorithms that are not only accurate but also objective and fair. Recent studies have shown that algorithmic decision making may be inherently prone to unfairness, even when there is no intention for it. This article presents an overview of the main concepts of identifying, measuring, and improving algorithmic fai

9. Bias and Unfairness in Machine Learning Models: A Systematic Review on Datasets, Tools, Fairness Metrics, and Identification and Mitigation Methods

   T. P. Pagano, R. B. Loureiro, F. V. Lisboa, et al. · 2023 · Big Data Cogn. Comput. · 280 citations

   One of the difficulties of artificial intelligence is to ensure that model decisions are fair and free of bias. In research, datasets, metrics, techniques, and tools are applied to detect and mitigate algorithmic unfairness and bias. This study examines the current knowledge on bias and unfairness in machine learning models. The systematic review followed the PRISMA guidelines and is registered on OSF plataform. The search was carried out between 2021 and early 2022 in the Scopus, IEEE Xplore, Web of Science, and Google Scholar knowledge bases and found 128 articles published between 2017 and 2022, of which 45 were chosen based on search string optimization and inclusion and exclusion criter

10. Beyond bias and discrimination: redefining the AI ethics principle of fairness in healthcare machine-learning algorithms

    Benedetta Giovanola, Simona Tiribelli · 2022 · AI & Society · 169 citations

    The increasing implementation of and reliance on machine-learning (ML) algorithms to perform tasks, deliver services and make decisions in health and healthcare have made the need for fairness in ML, and more specifically in healthcare ML algorithms (HMLA), a very important and urgent task. However, while the debate on fairness in the ethics of artificial intelligence (AI) and in HMLA has grown significantly over the last decade, the very concept of fairness as an ethical value has not yet been sufficiently explored. Our paper aims to fill this gap and address the AI ethics principle of fairness from a conceptual standpoint, drawing insights from accounts of fairness elaborated in moral phil

11. Algorithmic fairness and bias mitigation for clinical machine learning with deep reinforcement learning

    Jenny Yang, A. Soltan, D. Eyre, et al. · 2023 · Nature Machine Intelligence · 119 citations

    As models based on machine learning continue to be developed for healthcare applications, greater effort is needed to ensure that these technologies do not reflect or exacerbate any unwanted or discriminatory biases that may be present in the data. Here we introduce a reinforcement learning framework capable of mitigating biases that may have been acquired during data collection. In particular, we evaluated our model for the task of rapidly predicting COVID-19 for patients presenting to hospital emergency departments and aimed to mitigate any site (hospital)-specific and ethnicity-based biases present in the data. Using a specialized reward function and training procedure, we show that our m

12. The Butterfly Effect in artificial intelligence systems: Implications for AI bias and fairness

    Emilio Ferrara · 2024 · Machine Learning with Applications · 97 citations

13. Algorithmic bias, data ethics, and governance: Ensuring fairness, transparency and compliance in AI-powered business analytics applications

    Julien Kiesse Bahangulu, Louis Owusu-Berko · 2025 · World Journal of Advanced Research and Reviews · 66 citations

    The widespread adoption of AI-powered business analytics applications has revolutionized decision-making, yet it has also introduced significant challenges related to algorithmic bias, data ethics, and governance. As organizations increasingly rely on machine learning and big data analytics for customer profiling, credit scoring, hiring decisions, and predictive analytics, concerns about fairness, transparency, and compliance have intensified. Algorithmic biases—often stemming from biased training data, flawed model assumptions, and insufficient diversity in datasets—can result in discriminatory outcomes, reinforcing societal inequalities and reputational risks for businesses. To address the

14. Bias, Fairness and Accountability with Artificial Intelligence and Machine Learning Algorithms

    Nengfeng Zhou, Zach Zhang, V. Nair, et al. · 2022 · International Statistical Review · 56 citations

    The advent of artificial intelligence (AI) and machine learning algorithms has led to opportunities as well as challenges in their use. In this overview paper, we begin with a discussion of bias and fairness issues that arise with the use of AI techniques, with a focus on supervised machine learning algorithms. We then describe the types and sources of data bias and discuss the nature of algorithmic unfairness. In addition, we provide a review of fairness metrics in the literature, discuss their limitations, and describe de‐biasing (or mitigation) techniques in the model life cycle.

15. Economics, Fairness and Algorithmic Bias

    Bo Cowgill, Catherine E. Tucker · SSRN Electronic Journal · 53 citations

16. Data augmentation for fairness-aware machine learning: Preventing algorithmic bias in law enforcement systems

    Ioannis Pastaltzidis, N. Dimitriou, K. Quezada-Tavárez, et al. · 2022 · Proceedings of the 2022 ACM Conference on Fairness, Accountability, and Transparency · 48 citations

    Researchers and practitioners in the fairness community have highlighted the ethical and legal challenges of using biased datasets in data-driven systems, with algorithmic bias being a major concern. Despite the rapidly growing body of literature on fairness in algorithmic decision-making, there remains a paucity of fairness scholarship on machine learning algorithms for the real-time detection of crime. This contribution presents an approach for fairness-aware machine learning to mitigate the algorithmic bias / discrimination issues posed by the reliance on biased data when building law enforcement technology. Our analysis is based on RWF-2000, which has served as the basis for violent acti

17. Should Fairness be a Metric or a Model? A Model-based Framework for Assessing Bias in Machine Learning Pipelines

    John P. Lalor, Ahmed Abbasi, Kezia Oketch, et al. · 2024 · ACM Transactions on Information Systems · 39 citations

    Fairness measurement is crucial for assessing algorithmic bias in various types of machine learning (ML) models, including ones used for search relevance, recommendation, personalization, talent analytics, and natural language processing. However, the fairness measurement paradigm is currently dominated by fairness metrics that examine disparities in allocation and/or prediction error as univariate key performance indicators (KPIs) for a protected attribute or group. Although important and effective in assessing ML bias in certain contexts such as recidivism, existing metrics don’t work well in many real-world applications of ML characterized by imperfect models applied to an array of instan

18. Towards a holistic view of bias in machine learning: bridging algorithmic fairness and imbalanced learning

    Damien Dablain, B. Krawczyk, N. Chawla · 2022 · Discover Data · 35 citations

    Machine learning (ML) is playing an increasingly important role in rendering decisions that affect a broad range of groups in society. This posits the requirement of algorithmic fairness, which holds that automated decisions should be equitable with respect to protected features (e.g., gender, race). Training datasets can contain both class imbalance and protected feature bias. We postulate that, to be effective, both class and protected feature bias should be reduced—which allows for an increase in model accuracy and fairness. Our method, Fair OverSampling (FOS), uses SMOTE (Chawla in J Artif Intell Res 16:321–357, 2002) to reduce class imbalance and feature blurring to enhance group fairne

19. Mitigating machine learning bias between high income and low–middle income countries for enhanced model fairness and generalizability

    Jenny Yang, Lei A. Clifton, N. Dung, et al. · 2024 · Scientific Reports · 33 citations

    Collaborative efforts in artificial intelligence (AI) are increasingly common between high-income countries (HICs) and low- to middle-income countries (LMICs). Given the resource limitations often encountered by LMICs, collaboration becomes crucial for pooling resources, expertise, and knowledge. Despite the apparent advantages, ensuring the fairness and equity of these collaborative models is essential, especially considering the distinct differences between LMIC and HIC hospitals. In this study, we show that collaborative AI approaches can lead to divergent performance outcomes across HIC and LMIC settings, particularly in the presence of data imbalances. Through a real-world COVID-19 scre

20. Addressing Algorithmic Bias in AI‐Driven HRM Systems: Implications for Strategic HRM Effectiveness

    Ruwan Bandara, Kumar Biswas, Shahriar Akter, et al. · 2025 · Human Resource Management Journal · 29 citations

    AI and machine learning algorithms are revolutionising the modern workplace by transforming HR functions to deliver superior outcomes for both employees and organisations. However, research shows that these algorithms often fail to deliver optimal HR solutions, primarily due to inherent biases. Developing capabilities to overcome algorithmic biases is critical for firms, as these biases present significant challenges to fairness and inclusivity in HR decision‐making, ultimately impacting the effectiveness of HR practices. To address this challenge, our study, grounded in the dynamic capability perspective, presents a model to address algorithmic biases in people management and achieve superi

21. Exploring Bias and Prediction Metrics to Characterise the Fairness of Machine Learning for Equity-Centered Public Health Decision-Making: A Narrative Review

    Shaina Raza, Arash Shaban-Nejad, Elham Dolatabadi, et al. · 2024 · IEEE Access · 20 citations

    The rapid advancement of Machine Learning (ML) represents novel opportunities to enhance public health research, surveillance, and decision-making. However, there is a lack of comprehensive understanding of algorithmic bias — systematic errors in predicted population health outcomes — resulting from the public health application of ML. The objective of this narrative review is to explore the types of bias generated by ML and quantitative metrics to assess these biases. We performed search on PubMed, MEDLINE, IEEE (Institute of Electrical and Electronics Engineers), ACM (Association for Computing Machinery) Digital Library, Science Direct, and Springer Nature. We used keywords to identify stu

22. Algorithmic Fairness and Bias Mitigation for Clinical Machine Learning: Insights from Rapid COVID-19 Diagnosis by Adversarial Learning

    J. Yang, A. Soltan, Y. Yang, et al. · 2022 · 13 citations

    Machine learning is becoming increasingly promi- nent in healthcare. Although its benefits are clear, growing attention is being given to how machine learning may exacerbate existing biases and disparities. In this study, we introduce an adversarial training framework that is capable of mitigating biases that may have been acquired through data collection or magnified during model development. For example, if one class is over-presented or errors/inconsistencies in practice are reflected in the training data, then a model can be biased by these. To evaluate our adversarial training framework, we used the statistical definition of equalized odds. We evaluated our model for the task of rapidly

23. Using Pareto simulated annealing to address algorithmic bias in machine learning

    William Blanzeisky, Padraig Cunningham · 2021 · The Knowledge Engineering Review · 10 citations

    Abstract Algorithmic bias arises in machine learning when models that may have reasonable overall accuracy are biased in favor of ‘good’ outcomes for one side of a sensitive category, for example gender or race. The bias will manifest as an underestimation of good outcomes for the under-represented minority. In a sense, we should not be surprised that a model might be biased when it has not been ‘asked’ not to be; reasonable accuracy can be achieved by ignoring the under-represented minority. A common strategy to address this issue is to include fairness as a component in the learning objective. In this paper, we consider including fairness as an additional criterion in model training and pr

24. Algorithmic Fairness and Bias Mitigation for Clinical Machine Learning: A New Utility for Deep Reinforcement Learning

    J. Yang, A. Soltan, D. Clifton · 2022 · 7 citations

    As machine learning-based models continue to be developed for healthcare applications, greater effort is needed in ensuring that these technologies do not reflect or exacerbate any unwanted or discriminatory biases that may be present in the data. In this study, we introduce a reinforcement learning framework capable of mitigating biases that may have been acquired during data collection. In particular, we evaluated our model for the task of rapidly predicting COVID-19 for patients presenting to hospital emergency departments, and aimed to mitigate any site-specific (hospital) and ethnicity-based biases present in the data. Using a specialized reward function and training procedure, we show