An AI-Assisted Stakeholder Coordination Algorithm for Optimizing Communication Flow in Cross-Functional Project Teams

Abstract

Effective stakeholder communication remains a critical determinant of performance in cross-functional project teams, particularly in complex and data-intensive environments such as construction, oil and gas, and information technology systems. Traditional coordination approaches, which rely on static communication structures and heuristic decision-making, often result in inefficiencies characterized by redundancy, latency, and suboptimal information flow. This study proposes an AI-Assisted Stakeholder Coordination (AISC) algorithm for optimizing communication flow using a mathematically grounded and data-driven framework. The proposed model represents stakeholder interactions as a weighted directed graph, where communication links are associated with cost, latency, and redundancy parameters. A multi-objective optimization formulation is developed to minimize communication cost, redundancy, and latency while maximizing information propagation efficiency. To enable adaptive coordination, the framework integrates reinforcement learning, allowing the system to learn optimal communication policies from dynamic project environments. The coordination process is formalized as a Markov decision problem, with learning driven by a reward function aligned with communication efficiency objectives. The findings establish that integrating artificial intelligence with graph-based optimization provides a robust and scalable solution for stakeholder coordination. The proposed framework offers practical applicability across multiple industries and supports integration with enterprise systems and collaboration platforms. Future work may extend the model through deep reinforcement learning, explainable AI, and blockchain-based communication traceability to enhance transparency and adaptability.