Many-to-Many Data Trading Algorithm Based on Double Auction Theory.

Nowadays, data-based analysis plays a crucial role in both academia and industry, and thus data has been recognized a valuable resource to be traded. Because data generated from various end devices is dispersive, heterogeneous and stored in a distributed way, an impartial and trustworthy platform is indeed essential to make a market for trading entities (data buyers and sellers). In a practical market, all the entities tend to maximize their profits rather than the overall social welfare, while the platform, instead, should focus on social welfare maximization by applying a sophisticated mechanism that is imperative to guide the entities to distribute data efficiently. In this paper, we propose the Many-to-Many Data Trading Algorithm (MMDTA), and then formulate a data trading model with multiple entities based on MMDTA. Finally, the simulations validate convergence behavior and economic properties of MMDTA which is effective in different market scales and with different market power. [ABSTRACT FROM AUTHOR]