Nowadays there are lots of predictive services for several domains such as stock market and bookmakers. The value delivered by these services relies on the quality of their predictions. This paper presents QuPreSS, a general framework which measures predictive service quality and guides the selection of the most accurate predictive service. To do so, services are monitored and their predictions are compared over time by means of forecast verification with observations. A systematic literature review was performed to design a service-oriented framework architecture that fits into the current body of knowledge. The service-oriented nature of the framework makes it extensible and interoperable, being able to integrate existing services regardless their heterogeneity of platforms and languages. Finally, we also present an instantiation of the generic framework architecture for the weather forecast domain, freely available at http://gessi.lsi.upc. edu/qupress/

Peer Reviewed