Fuzzy Inference Models for Trust and Reputation Computation in Peer-to-Peer Systems, Slides of Fundamentals of E-Commerce

Download Fuzzy Inference Models for Trust and Reputation Computation in Peer-to-Peer Systems and more Slides Fundamentals of E-Commerce in PDF only on Docsity! Fuzzy Models • Use fuzzy inferences to handle uncertainties, f i d i luzz ness, an ncomp eteness. Based on the idea that in a P2P transaction• system evaluation and dissemination of trust can’t be effectively done and actors rely on collection of other’s opinions. Global reputation computation is time consuming • 2 Major inference steps Local Trust Inference Global Reputation Computation Docsity.com Trust and Reputation Inference • Buyer’s local trust score = f(payment method, payment time) • Seller’s local trust score = g(shipping time, goods quality) • Global Reputation weight = h(peer’s trust score transaction a/m transaction date) , , Where f, g, h are fuzzy inference functions Docsity.com Overlay Computation • DHT (Distributed Hash table) algorithm (Yideu M i l 2008)e et a Each peer maintains 2 tables: a transaction record table and the peers’ trust scores. The transaction record information is used for computing weights To make the algorithm scalable an aggregation threshold is i i d d h i h ib i b lma nta ne an peers w ose we g t contr ut ons are e ow this threshold are not queried for trust scores. Docsity.com PowerTrust (Zhu, Hwang 2006) • Uses the same architecture as FuzzyTrust discovers and uses Power Law matters in the trust system. Uses power trust scores to aggregate efficiently. Uses lookahead random walk and locality i h h i DHT t f R t tipreserv ng as n o per orm epu a on Aggregation Docsity.com PeerTrust (Liong, Xiu 2004) • Trust score of a peer is computed as the average of the scores weighted by the feedback of the peers • Scores based on 5 factors – peer record, credibility, transaction context, community context and scope, Docsity.com