Traders that operate in markets with multiple competing marketplaces can use learning to choose in which marketplace they will trade, and how much they will shout in that marketplace. If traders are able to share information with each other about their shout price and market choice over a social network, they can trend towards the market equilibrium more quickly, leading to higher profits for individual traders, and a more efficient market overall. However, if some traders share false information, profit and market efficiency can suffer as a result of traders acting on incorrect information. We present the Trading Agent Trust Model (TATM) that individual traders employ to detect deceptive traders and mitigate their influence on the individual’s actions. Using the JCAT double-auction simulator, we assess TATM by performing an experimental evaluation of traders sharing information about their actions over a social network in the presence of deceptive traders. Results indicate that TATM is effective at mitigating traders sharing false information, and can increase the profit of TATM traders relative to non-TATM traders.