Abstract

Proceedings Abstracts of the Twenty-Third International Joint Conference on Artificial Intelligence

A Framework to Choose Trust Models for Different E-Marketplace Environments / 213
Athirai A. Irissappane, Siwei Jiang, Jie Zhang

Many trust models have been proposed to evaluate seller trustworthiness in multiagent e-marketplaces. Their performance varies highly depending on environments where they are applied. However, it is challenging to choose suitable models for environments where ground truth about seller trustworthiness is unknown (called unknown environments). We propose a novel framework to choose suitable trust models for unknown environments, based on the intuition that if a model performs well in one environment, it will do so in another similar environment. Specifically, for an unknown environment, we identify a similar simulated environment (with known ground truth) where the trust model performing the best will be chosen as the suitable solution. Evaluation results confirm the effectiveness of our framework in choosing suitable trust models for different environments.