Bias Mitigation in Big Data Systems: A Systematic Review, Comparative Synthesis, and Decision Framework for Fair Algorithm Design
Abstract
As Big Data systems increasingly shape decision-making across healthcare, finance, hiring, criminal justice, and public governance, concerns regarding algorithmic bias and unfair outcomes have become more pronounced. While data-driven systems can improve efficiency, prediction, and service delivery, they may also reproduce historical inequalities through biased datasets, proxy variables, flawed labels, or opaque optimization processes.This study presents a systematic review and comparative synthesis of bias mitigation strategies in Big Data systems, with the aim of identifying effective approaches for fair algorithm design. Guided by a PRISMA-informed review methodology, literature published between 2018 and 2026 was screened across major academic databases, resulting in 27 studies included for final analysis.The findings classify mitigation approaches into pre-processing, in-processing, post-processing, and hybrid methods. Pre-processing techniques were found effective for addressing representation imbalance and data quality issues, while in-processing methods provided stronger fairness control where model retraining was feasible. Post-processing approaches were most practical for legacy or proprietary systems, whereas hybrid strategies were strongest in high-risk contexts requiring layered safeguards. The review further shows that no single fairness metric or mitigation technique is universally optimal; effectiveness depends on domain risk, bias source, regulatory obligations, and operational constraints.Based on these findings, the paper proposes the Fair Algorithm Design Decision Framework to guide organizations in selecting context-appropriate fairness interventions. The study concludes that bias mitigation should be treated as a continuous lifecycle responsibility integrating data governance, model design, human oversight, and ongoing monitoring.References
]Hossin, M.A., Du, J., Mu, L. and Asante, I.O. (2023) ‘Big Data-Driven Public Policy Decisions: Transformation toward smart Governance’, SAGE Open, 13(4). Available at: https://journals.sagepub.com/doi/full/10.1177/215
]Aljehani, S. B., Abdo, K. W., Alam, M. N., & Aloufi, E. M. (2024) ‘Big Data Analytics and Organizational Performance: Mediating roles of green innovation and knowledge management in telecommunications’, Sustainability, 16(18), 7887. Available at: https://doi.org/10.3390/su16187887
]Chohlas-Wood, A., Coots, M., Goel, S. and Nyarko, J. (2023) ‘Designing equitable algorithms’, Nature Computational Science, Perspective. Available at: https://doi.org/10.1038/s43588-023-00485-4
]Mittelstadt, B.D., Allo, P., Taddeo, M., Wachter, S. and Floridi, L. (2016) ‘The ethics of algorithms: Mapping the debate’, Big Data & Society, July–December, pp. 1–21. Available at: https://doi.org/10.1177/2053951716679679
]Cockcroft, S. and Russell, M. (2018) ‘Big data opportunities for accounting and finance practice and research: Big data in accounting and finance’, Australian Accounting Review, 28(3), pp.323–333. Available at: https://doi.org/10.1111/auar.12218
]Hanna, M., Pantanowitz, L., Jackson, B., Palmer, O., Visweswaran, S., Pantanowitz, J., Deebajah, M., & Rashidi, H. (2024) ‘Ethical and bias considerations in artificial intelligence (AI)/Machine learning’, Modern Pathology, 100686. Available at: https://doi.org/10.1016/j.modpat.2024.100686
]Hasanzadeh, F., Azizi, Z., White, J.A., Josephson, C.B. and Waters, G. (2025) ‘Bias recognition and mitigation strategies in artificial intelligence healthcare applications’, npj Digital Medicine, 8(154). Available at: https://doi.org/10.1038/s41746-025-01503-7
]Shahul Hameed, M.A., Qureshi, A.M. and Kaushik, A. (2024) ‘Bias mitigation via synthetic data generation: A review’, Electronics, 13(3909). Available at: https://doi.org/10.3390/electronics13193909
]Chen, S., Keglovits, M., Devine, M., & Stark, S. (2021) ‘Sociodemographic differences in respondent preferences for survey formats: sampling bias and potential threats to external validity’, Archives of Rehabilitation Research and Clinical Translation, 4(1), 100175. Available at: https://doi.org/10.1016/j.arrct.2021.100175
]Ho, J. Q., Hartanto, A., Koh, A., & Majeed, N. M. (2025) ‘Gender Biases within Artificial Intelligence and ChatGPT: Evidence, Sources of Biases and Solutions’, Computers in Human Behavior Artificial Humans, 100145. Available at: https://doi.org/10.1016/j.chbah.2025.100145
]Köchling, A., & Wehner, M. C. (2020) ‘Discriminated by an algorithm: a systematic review of discrimination and fairness by algorithmic decision-making in the context of HR recruitment and HR development’, BuR - Business Research, 13(3), 795–848. Available at: https://doi.org/10.1007/s40685-020-00134-w
]Joseph, J. (2024) ‘Predicting crime or perpetuating bias? The AI dilemma’, AI & Society, 40, pp 2319–2321 Available at: https://doi.org/10.1007/s00146-024-02032-9
]Chen, Z. (2023) ‘Ethics and discrimination in artificial intelligence-enabled recruitment practices’, Humanities and Social Sciences Communications, 10(1). Available at: https://doi.org/10.1057/s41599-023-02079-x
]Belenguer, L. (2022) ‘AI bias: exploring discriminatory algorithmic decision-making models and the application of possible machine centric solutions adapted from the pharmaceutical industry’, AI Ethics, 2(4), pp.771–787. Available at: https://doi.org/10.1007/s43681-022-00138-8
]Favier, M., Calders, T., Pinxteren, S., & Meyer, J. (2023) ‘How to be fair? A study of label and selection bias’, Machine Learning, 112(12), 5081–5104. Available at: https://doi.org/10.1007/s10994-023-06401-1
]Ferrara, E. (2023) ‘Fairness and Bias in Artificial intelligence: A brief survey of sources, impacts, and mitigation strategies’, Sci, 6(1), 3. Available at: https://doi.org/10.3390/sci6010003
]Candanosa, R.M., Fernandes, G.S.P., Uliana, J.H., Bachmann, L., Carneiro, A.A.O. and Pavan, T.Z. (2023) ‘Medical imaging fails dark skin: Researchers fixed it’, ScienceDaily-. Johns Hopkins University Available at: https://www.sciencedaily.com/releases/2023/10/231010133534.htm (Accessed: 23 July 2025).
]Varsha, P.S. (2023) ‘How can we manage biases in artificial intelligence systems – A systematic literature review’, International Journal of Information Management Data Insights, 3(1), Article 100165. Available at: https://doi.org/10.1016/j.jjimei.2023.100165
]Ukanwa, K. (2024). Algorithmic bias: Social science research integration through the 3-D Dependable AI Framework. Current Opinion in Psychology, 58, 101836. Available at: https://doi.org/10.1016/j.copsyc.2024.101836
]Wang, X., Wu, Y. C., Ji, X., & Fu, H. (2024). Algorithmic discrimination: examining its types and regulatory measures with emphasis on US legal practices. Frontiers in Artificial Intelligence, 7. Available at: https://doi.org/10.3389/frai.2024.1320277
]Farayola, M. M., Tal, I., Saber, T., Connolly, R., & Bendechache, M. (2025). A fairness-focused approach to recidivism prediction: implications for accuracy, trust, and equity. AI & Society. https://doi.org/10.1007/s00146-025-02452-1
]Singh, N., Kapoor, A., & Soni, N. (2024). A sociotechnical perspective for explicit unfairness mitigation techniques for algorithm fairness. International Journal of Information Management Data Insights, 4(2), 100259. https://doi.org/10.1016/j.jjimei.2024.100259
]Mbah, G.O. (2024) ‘Data privacy in the era of AI: Navigating regulatory landscapes for global businesses’, International Journal of Science and Research Archive, 13(2), pp.2040–2058. Available at: https://doi.org/10.30574/ijsra.2024.13.2.2396
]Holstein, J., Schemmer, M., Jakubik, J., Vössing, M., & Satzger, G. (2023) ‘Sanitizing data for analysis: Designing systems for data understanding’, Electronic Markets, 33(1). Available at: https://doi.org/10.1007/s12525-023-00677-w
]Hosseinzadeh, M., Azhir, E., Ahmed, O.H. and Ghafour, M.Y. (2021) ‘Data cleansing mechanisms and approaches for big data analytics: a systematic study’, Journal of Ambient Intelligence and Humanized Computing, 14(4), pp.1–13. Available at: https://doi.org/10.1007/s12652-021-03590-2
]Qi, X., Chen, G., Li, Y., Cheng, X., & Li, C. (2019) ‘Applying Neural-Network-Based Machine Learning to Additive Manufacturing: Current applications, challenges, and future Perspectives’. Engineering, 5(4), 721–729. Available at: https://doi.org/10.1016/j.eng.2019.04.012
]Almasoud, A.S. and Idowu, J.A. (2025) ‘Algorithmic fairness in predictive policing’, AI Ethics, 5, pp.2323–2337. Available at: https://doi.org/10.1007/s43681-024-00541-3
]Kusche, I. (2024) ‘Possible harms of artificial intelligence and the EU AI act: fundamental rights and risk’, Journal of Risk Research, 27(6). Available at: https://doi.org/10.1080/13669877.2024.2350720
]Hagendorff, T. (2020). The Ethics of AI Ethics: An Evaluation of Guidelines. Minds and Machines, 30(1), 99–120. Available at: https://doi.org/10.1007/s11023-020-09517-8
DOI:
https://doi.org/10.31449/inf.v50i2.10456Downloads
Published
Issue
Section
License
Authors retain copyright in their work. By submitting to and publishing with Informatica, authors grant the publisher (Slovene Society Informatika) the non-exclusive right to publish, reproduce, and distribute the article and to identify itself as the original publisher.
All articles are published under the Creative Commons Attribution license CC BY 3.0. Under this license, others may share and adapt the work for any purpose, provided appropriate credit is given and changes (if any) are indicated.
Authors may deposit and share the submitted version, accepted manuscript, and published version, provided the original publication in Informatica is properly cited.
