Collective intelligence as a framework for supply chain management

The supply chain management is a difficult problem to solve in the context of distributed (information across different geographical locations) and dynamic (changes in the structure and content of the information) environment with multidisciplinary decisions (employees' decision making at different levels). In this research work, an approach to the dynamic optimization of local decisions to assure global optimization in supply chain performance is developed within the framework of a collective intelligence (COIN). As a COIN, we mean a large multi-agent system where there is no centralized control and communication, but also, there is a global task to complete. The proposed framework is focused on the interactions at local and global levels with the agents in order to improve the overall supply chain business process behaviour. Besides, learning consists of adapting the local behavior of each entity with the aim of optimizing a given global behavior. Reinforcement learning algorithms are used at the local level, while generalization of Q-neural algorithm is used to optimize the global behavior. The framework is implemented over an agent platform. The work demonstrates that this problem is a good experimental field for the investigation and application of the COIN theory.