Mercury

A Tool for Selecting the Most Accurate Weather Predictive Service based on QuPreSS Reference Model

Goals of the Project

This project has two goals:

  • A Reference Model for the Prediction Problem: QuPreSS.
  • A Tool for the Weather Forescast Domain: Mercury.

Features and Use of the Tool

Mercury is available in three ways: a web client application, a web service, and a virtual machine:

  • Virtual Machine: Mercury is available on a virtual machine inside theWaSDeTT 2013 bundle of SHARE. The virtual machine of Mercury contains a fully self-contained demo without internet access. For testing purposes, it includes the Forecast Verifier web client and a historic data set collected from July 2011 to March 2014.

Downloads

Here you can download a .zip file that includes:

Publications

You can find more information and documentation in the next publications:

  • [PDF] [DOI] S. Martínez-Fernández, X. Franch, and J. Bisbal, “Mercury: Using the QuPreSS Reference Model to Evaluate Predictive Services,” Science of Computer Programming, 2015. Accepted Manuscript in the Experimental Software and Toolkits (EST 6): A special issue of the Workshop on Academic Software Development Tools and Techniques (WASDeTT 2013). [Impact Factor: 0.715, Q3, JCR 2014].
    [Bibtex] 
    @article{martinez-fernandez2016mercury,
author = {Mart\'{\i}nez-Fern\'{a}ndez, Silverio and Franch, Xavier and Bisbal, Jesus},
journal = {{Science of Computer Programming}},
keywords = {tool development, predictive services, reference model, forecast verification, service monitoring},
title = {{Mercury: Using the QuPreSS Reference Model to Evaluate Predictive Services}},
year = "2015",
issn = "0167-6423",
doi = "10.1016/j.scico.2015.11.009",
url = "http://www.sciencedirect.com/science/article/pii/S0167642315004050",
note = {Accepted Manuscript in the Experimental Software and Toolkits (EST 6): A special issue of the Workshop on Academic Software Development Tools and Techniques (WASDeTT 2013). [Impact Factor: 0.715, Q3, JCR 2014]}
}
  • [PDF] S. Martínez-Fernández, X. Franch, and J. Bisbal, “Verifying predictive services’ quality with Mercury,” in 4th International Workshop on Academic Software Development Tools and Techniques (WASDeTT), 2013.
    [Bibtex] 
    @inproceedings{martinez-fernandez2013mercury,
author = {Mart\'{\i}nez-Fern\'{a}ndez, Silverio and Franch, Xavier and Bisbal, Jes\'{u}s},
booktitle = {{4th International Workshop on Academic Software Development Tools and Techniques (WASDeTT)}},
keywords = {forecast verification,predictive services,selection,service,service monitoring,service-oriented architecture,tool development},
title = {{Verifying predictive services' quality with Mercury}},
url = {http://wasdett.org/2013/submissions/wasdett2013\_submission\_6.pdf http://upcommons.upc.edu/e-prints/handle/2117/21145},
year = {2013}
}
  • [PDF] [DOI] S. Martínez-Fernández, J. Bisbal, and X. Franch, “QuPreSS: A Service-Oriented Framework for Predictive Services Quality Assessment,” in 7th International Conference on Knowledge Management in Organizations: Service and Cloud Computing (KMO 2012), 2012, p. 525–536.
    [Bibtex] 
    @inproceedings{martinez-fernandez2012qupress,
abstract = {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/.},
author = {Mart\'{\i}nez-Fern\'{a}ndez, Silverio and Bisbal, Jes\'{u}s and Franch, Xavier},
booktitle = {{7th International Conference on Knowledge Management in Organizations: Service and Cloud Computing (KMO 2012)}},
doi = {10.1007/978-3-642-30867-3\_47},
pages = {525--536},
title = {{QuPreSS: A Service-Oriented Framework for Predictive Services Quality Assessment}},
url = {http://link.springer.com/chapter/10.1007/978-3-642-30867-3\_47},
year = {2012}
}
  • [PDF] S. Martínez-Fernández, “Accuracy Assessment of forecasting services,” Master Thesis, 2011. Advisors: Xavier Franch and Jesus Bisbal.
    [Bibtex] 
    @mastersthesis{martinez-fernandez2011accuracy,
author = {Mart\'{\i}nez-Fern\'{a}ndez, Silverio},
publisher = {Universitat Polit\`{e}cnica de Catalunya},
title = {{Accuracy Assessment of forecasting services}},
url = {http://upcommons.upc.edu/pfc/handle/2099.1/13105},
school={Universitat Polit\`{e}cnica de Catalunya (UPC). BarcelonaTech},
year = {2011},
note={Advisors: Xavier Franch and Jesus Bisbal}
}
  • [PDF] S. Martínez-Fernández, J. Bisbal, and X. Franch, Accuracy Assessment of Forecasting Services (poster). 1st European Business Intelligence Summer School (eBISS), 2011.
    [Bibtex] 
    @misc{martinez-fernandez2011ebiss,
author={Mart\'{\i}nez-Fern\'{a}ndez, Silverio and Bisbal, Jes\'{u}s and Franch, Xavier},
title={{Accuracy Assessment of Forecasting Services (poster). 1st European Business Intelligence Summer School (eBISS)}},
howpublished={1st European Business Intelligence Summer School (eBISS)},
year={2011}
}