Mitigating Artificial Intelligence Bias in Financial Systems: A Comparative Analysis of Debiasing Techniques
Asian Journal of Research in Computer Science · pp. 165–178 · Published 19 Dec 2024
10.9734/ajrcos/2024/v17i12536Abstract
Balancing fairness and predictive accuracy remains a key challenge in AI system development. This study investigates the origins of AI bias, how it happens in business processes, and the challenges it poses to ethical and transparent decision-making. Drawing on existing literature, the research explores the various types of biases—including cognitive, algorithmic, and representation biases—and their impact on AI systems in the BFSI sector. Furthermore, the study critically evaluates current debiasing techniques, such as pre-processing, fairness-aware models, and post-processing, highlighting their limitations in balancing fairness with predictive accuracy. This study aims to advance the development of more equitable AI systems in the BFSI sector by proposing the FAIR-BIAS Framework. This framework provides a structured approach to detecting, mitigating, and monitoring biases in AI models. Key recommendations include implementing equalized odds as a fairness metric to ensure balanced outcomes across demographic groups, applying adversarial debiasing techniques during model training to minimize discriminatory effects, and conducting regular data audits to ensure long-term fairness. The findings offer direct benefits for BFSI stakeholders. Businesses can enhance the reliability and ethical integrity of AI models by adopting fairness-aware risk assessments, which promote compliance and customer trust. Regulators can enforce accountability by mandating transparency measures, such as model explainability, and conducting periodic audits using fairness metrics like equalized odds. Policymakers can use the insights to create inclusive legislation which requires fairness testing and transparency in AI applications. Future research could explore the long-term effectiveness of debiasing techniques across different industries, such as healthcare or public policy, by conducting longitudinal studies to assess how evolving datasets and models influence fairness outcomes. It is critical for BFSI organizations to adopt these frameworks and techniques to foster a more inclusive and ethical future in financial services.”
References (5)
- 1 Algorithmic bias in machine learning-based marketing models [DOI]
- 2 Algorithmic equity in the hiring of underrepresented IT job candidates [DOI]
- 3 Enhancing audit accuracy: The role of AI in detecting financial anomalies and fraud [DOI]
- 4 The impact of overconfidence and herding bias on stock investment decisions mediated by risk perception [DOI]
- 5 Understanding Unfairness in Fraud Detection through Model and Data Bias Interactions [DOI]
Cited by 53
Shengyuan Tang, Linwan Zhang, Shengzhe Xu · Electronics · 2025
Sukriti Bhattacharya, German Castignani, Leandro Masello · Frontiers in Artificial Intelligence · 2025
Osman Kurter · OPUS Toplum Araştırmaları Dergisi · 2025
Peiyi Zhou · Advances in Economics and Management Research · 2025
Maria Kocot, Artur Kwasek, Krzysztof Bondyra · Journal for Perspectives of Economic Political and Social Integration · 2025
Hadeel Yaseen, Asma’a Al-Amarneh · Journal of Risk and Financial Management · 2025
Rahul Rishi Sharma, Deepankar Dixit, Vamshi krishna Ayyam · 2025 IEEE 5th International Conference on ICT in Business Industry & Government (ICTBIG) · 2025
Showing 17 of 53 known citations — external sources report more than can currently be individually listed.
Related research
- Ethical AI in the Healthcare Sector: Investigating Key Drivers of Adoption through the Multi-Dimensional Ethical AI Adoption Model (MEAAM) — shares topic coverage
- Algorithmic Precision Medicine: Harnessing Artificial Intelligence for Healthcare Optimization — shares topic coverage
- The Role of Data Science in Improving Healthcare Access and Equity — shares topic coverage
- Generative AI in Supply Chain: A Systematic Review of Opportunities, Benefits, and Challenges — shares topic coverage
- Generative AI for Personalised Marketing Campaign Design and Content Automation — shares topic coverage
Article metrics
Real usage data collected on this platform.
41
Page views
0
PDF downloads
4
Outbound clicks
53
Citations
Views over time
Views by country
Approximate, from request IP at view time — not citizenship or institution. Countries with fewer than 5 views are grouped as "Other".
Traffic sources
Referring site, by host.
Views and downloads exclude known bots/crawlers. Citations combines this platform's own DOI-resolved index with each external source's own reported total — see Cited by above for individually listed citing works. Last refreshed 0 seconds ago.