CellTrust: a reputation model for C2C commerce

Abstract

The improvement of wireless technologies and the increasing spread of mobile phones open new possibilities to perform mobile Customer-to-Customer commercial activities. In this new scenario, where users cannot rely on stable connections, it assumes a great relevance how to trust the counterpart in a transaction and how to avoid that a disconnection, possible in wireless connections, can encourage users to cheat. To tackle these issues we propose a feedback-based reputation mechanism able to detect malicious users better than other state-of-the-art techniques, as shown by the large number of experiments run to measure the accuracy of the compared methods in the most common situations.

An Evaluation Method of the Drafting Unit of National Standard Based on AHP

“…AHP is a decision-making method of qualitative and quantitative analysis which would resolve the elements related to the decision into objectives, principles and scheme [3].…”

A Multi Dimension Service Trust Model in Social Network

“…The multidimensional service trust model (Mmodel) has proposed algorithm in different situations, which can improve the trust computation efficiency. In order to verify the accuracy of the model trust calculation, the following error indicators are set as follows [13].…”

Cloning mechanisms to improve agent performances

“…In large and dynamic agent societies, some authors consider the possibility to adopt a reputation system (Van Vugt et al, 2007) to support future agent interactions. Reputation models, in order to represent the trustworthiness of an agent, considers a lot of malicious behaviors possibly adopted to avoid a correct perception of the reputation (the interesting reader can refer to Conte and Paolucci (2002), Sabater and Sierra (2005) In many models the different reputation sources are often evaluated by weighing their credibility (Sabater and Sierra, 2001;Conte and Paolucci, 2002;Ruthanna and Spears, 2012;Lax and Sarné , 2008), usually represented by their own reputation while in EVA is used the F b -measure. Furthermore, in the ''genealogic'' reputation approach of EVA the contribution to the reputation of an agent due to its ancestors is weighted by genealogic distances.…”

“…At the best of our knowledge, no other system adopts this approach to obtain a sort of ''forgiveness'' effect, commonly based on temporal considerations (Marsh and Briggs, 2009). However, other decay laws could be exploited as in CellTrust (Lax and Sarné , 2008) where it is adopted an exponential decay law that is time independent.…”