Explainable Human AI Decision Intelligence for Executive Strategy Development Using Enterprise Documents and Real-Time Business Signals

Abstract

The growing complexity of enterprise environments has increased the need for decision intelligence systems that can integrate organizational knowledge, real-time business conditions, and transparent reasoning into executive strategy development. This study proposes an explainable decision intelligence framework that combines enterprise documents, live business signals, contextual retrieval, evidence fusion, strategic prioritization, and traceable explanation generation within a unified architecture. The framework was evaluated through five analytical dimensions covering retrieval quality, contextual fusion, recommendation strength, explainability performance, and executive validation. The results showed that signal-aware retrieval consistently outperformed document-only retrieval across six executive query categories, with Precision@5 increasing from 0.67-0.74 to 0.80-0.86. Growth slowdown achieved the highest retrieval performance at 0.86, followed by operational delay at 0.85 and cost pressure at 0.84. Contextual fusion analysis further indicated strong document-signal alignment in finance and risk domains, with context link strengths of 0.88 and 0.85, respectively, while bundle density reached 14 evidence items in finance and 13 in risk. In the recommendation layer, operational stabilization received the highest strategic priority score at 0.87, followed by cost restructuring at 0.82 and selective expansion at 0.78, showing that the framework could differentiate between corrective, defensive, and growth-oriented strategies according to current business conditions. Explainability results revealed that recommendation logic was distributed across multiple factors, with margin pressure contributing 29% of explanation weight, execution delay 24%, demand instability 18%, risk exposure 15%, and strategic fit 14%, indicating balanced and evidence-grounded reasoning rather than single-factor dominance. Executive validation also produced strong outcomes, with average ratings of 4.8 for decision support, 4.7 for evidence grounding, 4.6 for clarity, 4.5 for trust, and 4.4 for actionability on a five-point scale. These findings demonstrate that the proposed framework improves strategic decision support by linking enterprise memory with live business signals and by presenting prioritized recommendations with transparent evidence trails. The study contributes a practical model for executive strategy development in dynamic enterprise settings, while also extending the literature on explainable AI, enterprise retrieval-augmented intelligence, and decision support system design.