iAdditive: fast and fair Shapley-inspired feature attribution forcorrelated features

Interpreting machine learning models fairly and efficiently remains challenging, particularly when features are correlated.Classical Shapley-based explanations can split attribution among substitutes and are often computationally demanding. Thisstudy presents iAdditive, a model-agnostic approach that promotes fairness by grouping highly correlated or redundant featuresthrough group-level attribution semantics and improves efficiency via a dynamic coalition heuristic inspired by additive expla-nation methods. Experiments on simulated datasets with known structure and on NHANES indicate that iAdditive producesfaithful global attributions under correlation while achieving substantial runtime reductions compared with KernelSHAP,TreeSHAP, SAGE, and exact Shapley baselines. By balancing fairness, interpretability, and efficiency, iAdditive provides apractical tool for trustworthy decision support in applications such as health care.