Nowadays, lots of service providers offer predictive services that show in advance a condition or occurrence about the future. As a consequence, it becomes necessary for service customers to select the predictive service that best satisfies their needs. The QuPreSS reference model provides a standard solution for the selection of predictive services based on the quality of their predictions. QuPreSS has been designed to be applicable in any predictive domain (e.g., weather forecasting, economics, and medicine). This paper presents Mercury, a tool based on the QuPreSS reference model and customized to the weather forecast domain. Mercury measures weather predictive services' quality, and automates the context-dependent selection of the most accurate predictive service to satisfy a customer query. To do so, candidate predictive services are monitored so that their predictions can be eventually compared to real observations obtained from a trusted source. Mercury is a proof-of-concept of QuPreSS that aims to show that the selection of predictive services can be driven by the quality of their predictions. Throughout the paper, we show how Mercury was built from the QuPreSS reference model and how it can be installed and used.

Peer Reviewed