Case-based Reasoning for Web Service Discovery and Selection
Alan De Renzis$^{1}$, Martin Garriga$^{1}$, Andres Flores$^{1}$, Alejandra Cechich$^{1}$, Alejandro Zunino$^{2}$
$^{1}$UNComa University. Neuquen Argentina,
$^{2}$Universidad Nacional del Centro de la Provincia de Buenos Aires. Buenos Aires Argentina
email: alanderenzis@fi.uncoma.edu.ar, martin.garriga@fi.uncoma.edu.ar, andres.flores@fi.uncoma.edu.ar, alejandra.cechich@fi.uncoma.edu.ar, azunino@gmail.com

Schedule:Wed 21st@18:15, Room: B

Web Service discovery and selection deal with the retrieval of the most suitable Web Service, given a required functionality. Addressing an effective solution remains difficult when only functional descriptions of services are available. In this paper, we propose a solution by applying Case-based Reasoning, in which the resemblance between a pair of cases is quantified through a similarity function. We show the feasibility of applying Case-based Reasoning for Web Service discovery and selection, by introducing a novel case representation, learning heuristics and three different similarity functions. We also experimentally validate our proposal with a dataset of 62 real-life Web Services, achieving competitive values in terms of well-known Information Retrieval metrics.

BibTex

@InProceedings{CLEI-2015:144239,
	author 		= {Alan De Renzis and Martin Garriga and Andres Flores and Alejandra Cechich and Alejandro Zunino},
	title 		= {Case-based Reasoning for Web Service Discovery and Selection},
	booktitle 	= {2015 XLI Latin American Computing Conference (CLEI), Special Edition},
	pages 		= {25--36},
	year 		= {2015},
	editor 		= {Universidad Católica San Pablo},
	address 	= {Arequipa-Peru},
	month 		= {October},
	organization 	= {CLEI},
	publisher 	= {CLEI},
	url 		= {http://clei.org/clei2015/144239},
	isbn 		= {978-9972-825-91-0},
	}