Document Type



Automated negotiation plays an important role in dynamic trading online, especially in B2C e-commerce, as it is crucially useful for the online merchants to achieve better trading outcomes and save vast trading cost. To address the critical issue, this paper develops a prediction strategy that using linear regression to predict the opponent’s future offer trend, the theoretical model and the algorithm are proposed. To demonstrate the effectiveness of this model, we develop a prototype and conduct computer-computer automated negotiation to make comparison with the previous negotiation strategy model. The experimental result shows that the agent with our newly designed strategy model can significantly increase the agreement rate and joint outcome of the both sides.