Adaptive Bias Fusion Using Kappa-Ordered Weight to Address Multi-Expert Disparity

Expert judgment bias presents challenges in decision-making, especially in complex fields like finance. This paper explores the dual nature of biases in multi-expert systems, where integrating diverse perspectives can reduce individual biases but also introduce inconsistencies that obscure coherent decisions. While multi-expert approaches enhance reliability, they can also lead to conflicting conclusions due to differing biases, compromising credibility and strategic alignment. To address these issues, we propose the adaptive Kappa-Ordered Weight Averaging (KOWA) method, which uses kappa statistics to integrate expert opinions, adjust for outliers, and promote consensus. Our case study shows that KOWA improves decision quality by enhancing transparency and accountability, increasing forecast accuracy, and boosting stakeholder confidence. This approach advances multi-expert decision-making, helping organizations align strategies with long-term goals in complex financial environments.