Game-Theoretic Decision Rights Allocation for Cross-Enterprise Data Sharing Under the Federated Learning FATE Framework Under the Data Legal Context

In modern automotive supply chains, enterprises such as manufacturers, component suppliers, and logistics providers are tightly interconnected yet reluctant to share operational data due to privacy, competitive, and regulatory concerns. While federated learning (FL) offers a technical pathway for collaborative model training without exposing raw data, most existing frameworks neglect the governance challenge of allocating decision rights among partners with diverse data quality, volume, and computational resources. This study proposes a game-theoretic decision rights allocation mechanism integrated into the FATE federated learning platform, designed to ensure fairness, efficiency, and stability in cross-enterprise data sharing. The method models each participant's contribution through a payoff function incorporating data utility, timeliness, and cost, and determines decision influence by solving for a cooperative Nash equilibrium under privacy constraints.