EUVIMEDEUVIMED entdecken
Systematische Übersicht

Bias Mitigation in Big Data Systems: A Systematic Review, Comparative Synthesis, and Decision Framework for Fair Algorithm Design

Daniel Kweku Assumang, Ifeoma Eleweke, Chiamaka Ezenwaka, Olabode Soetan, Martin Msughter Vincent, Elizabeth Ayodeji Adeyefa

Informatica · 04.08.2026 · 50 (2)

DOI: 10.31449/inf.v50i2.10456 ↗

Kurz gefasst

Systematische Übersicht in der Zeitschrift Informatica, online erschienen am 04.08.2026. Verfasst von Daniel Kweku Assumang und 5 weiteren Autor:innen.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

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.

Zitieren

APA

Assumang, D. K., Eleweke, I., Ezenwaka, C., Soetan, O., Vincent, M. M., & Adeyefa, E. A. (2026). Bias Mitigation in Big Data Systems: A Systematic Review, Comparative Synthesis, and Decision Framework for Fair Algorithm Design. Informatica, 50(2). https://doi.org/10.31449/inf.v50i2.10456

Vancouver

Assumang DK, Eleweke I, Ezenwaka C, Soetan O, Vincent MM, Adeyefa EA. Bias Mitigation in Big Data Systems: A Systematic Review, Comparative Synthesis, and Decision Framework for Fair Algorithm Design. Informatica. 2026;50(2). doi:10.31449/inf.v50i2.10456

BibTeX
@article{Assumang2026,
  author = {Assumang, Daniel Kweku and Eleweke, Ifeoma and Ezenwaka, Chiamaka and Soetan, Olabode and Vincent, Martin Msughter and Adeyefa, Elizabeth Ayodeji},
  title = {Bias Mitigation in Big Data Systems: A Systematic Review, Comparative Synthesis, and Decision Framework for Fair Algorithm Design},
  journal = {Informatica},
  year = {2026},
  volume = {50},
  number = {2},
  doi = {10.31449/inf.v50i2.10456}
}
Kostenlos starten →