Search

We propose a novel trust metric for social networks which is suitable for application in recommender systems. It is personalised and dynamic and allows to compute the indirect trust between two agents which are not neighbours based on the direct trust between agents that are neighbours. In analogy to some personalised versions of PageRank, this metric makes use of the concept of feedback centrality and overcomes some of the limitations of other trust metrics.In particular, it does not neglect cycles and other patterns characterising social networks, as some other algorithms do. In order to apply the metric to recommender systems, we propose a way to make trust dynamic over time. We show by means of analytical approximations and computer simulations that the metric has the desired properties. Finally, we carry out an empirical validation on a dataset crawled from an Internet community and compare the performance of a recommender system using our metric to one using collaborative filtering., Comment: Revised, added Empirical Validation, submitted to Recommender Systems 2009

We study the performance of various agent strategies in an artificial investment scenario. Agents are equipped with a budget, $x(t)$, and at each time step invest a particular fraction, $q(t)$, of their budget. The return on investment (RoI), $r(t)$, is characterized by a periodic function with different types and levels of noise. Risk-avoiding agents choose their fraction $q(t)$ proportional to the expected positive RoI, while risk-seeking agents always choose a maximum value $q_{max}$ if they predict the RoI to be positive ("everything on red"). In addition to these different strategies, agents have different capabilities to predict the future $r(t)$, dependent on their internal complexity. Here, we compare 'zero-intelligent' agents using technical analysis (such as moving least squares) with agents using reinforcement learning or genetic algorithms to predict $r(t)$. The performance of agents is measured by their average budget growth after a certain number of time steps. We present results of extensive computer simulations, which show that, for our given artificial environment, (i) the risk-seeking strategy outperforms the risk-avoiding one, and (ii) the genetic algorithm was able to find this optimal strategy itself, and thus outperforms other prediction approaches considered., Comment: 27 pp. v2 with minor corrections. See http://www.sg.ethz.ch for more info

In this paper, we present a model of a trust-based recommendation system on a social network. The idea of the model is that agents use their social network to reach information and their trust relationships to filter it. We investigate how the dynamics of trust among agents affect the performance of the system by comparing it to a frequency-based recommendation system. Furthermore, we identify the impact of network density, preference heterogeneity among agents, and knowledge sparseness to be crucial factors for the performance of the system. The system self-organises in a state with performance near to the optimum; the performance on the global level is an emergent property of the system, achieved without explicit coordination from the local interactions of agents., Comment: v3 revised as compared to v2 (figures updated, clarifications). Accepted for publication in J. Autonomous Agents and Multi-Agent Systems (2007)