Cardiff University | Prifysgol Caerdydd ORCA
Online Research @ Cardiff 
WelshClear Cookie - decide language by browser settings

Improving resource matchmaking through feedback integration

Haas, Christian, Petri, Ioan and Rana, Omer Farooq 2014. Improving resource matchmaking through feedback integration. Presented at: 2014 14th IEEE/ACM International Symposium on Cluster, Cloud and Grid Computing (CCGrid), Chicago, IL, USA, 26-29 May 2014. Cluster, Cloud and Grid Computing (CCGrid), 2014 14th IEEE/ACM International Symposium on. IEEE, pp. 906-914. 10.1109/CCGrid.2014.28

Full text not available from this repository.

Abstract

Distributed systems in which users consume and supply different types of services and resources are becoming ever more prevalent. For the matching of consumers and providers, preference-based two-sided matching algorithms can be used to improve the efficiency of the overall match outcome. In such systems, requesting (providing) users rank others based on preferences derived from feedback. Trust can be inferred using trust networks through direct or indirect feedback based on previous actions, and influences the preference ranking that users submit to the matching algorithm. As feedback influences the preference ranking and thus the matching, in this paper we propose a novel methodology which makes use of feedback in the decision making of preference rankings, in order to avoid being matched to untrustworthy users (or provides not likely to deliver their service). We use a simulation based validation approach to determine the effects of dynamic/continuous feedback and its influence on preference ranking of providers.

Item Type: Conference or Workshop Item (Paper)
Date Type: Publication
Status: Published
Schools: Computer Science & Informatics
Subjects: Q Science > QA Mathematics > QA75 Electronic computers. Computer science
Publisher: IEEE
Last Modified: 20 Dec 2017 02:38
URI: http://orca.cf.ac.uk/id/eprint/66158

Citation Data

Cited 1 time in Google Scholar. View in Google Scholar

Cited 1 time in Scopus. View in Scopus. Powered By Scopus® Data

Actions (repository staff only)

Edit Item Edit Item