Self Organizing Supply Chains for Micro-Prediction: Present and Future uses of the ROAR Protocol
This addresses the problem of generating cost-effective predictions for organizations, but it appears incremental as it builds on existing multi-agent and crowd-sourcing concepts.
The paper trialed a multi-agent system for crowd-sourcing inexpensive, high-quality prediction streams using agents with statistical models and economic self-interest, reporting empirical lessons from firm employees and suggesting a future trajectory toward a Prediction Web.
A multi-agent system is trialed as a means of crowd-sourcing inexpensive but high quality streams of predictions. Each agent is a microservice embodying statistical models and endowed with economic self-interest. The ability to fork and modify simple agents is granted to a large number of employees in a firm and empirical lessons are reported. We suggest that one plausible trajectory for this project is the creation of a Prediction Web.