基于相关向量机的协商决策模型

Relevance Vector Machine Based Negotiation Decision Model

为了进一步提高电子商务中对手协商偏好估计的精度,该文提出了一种基于相关向量机(Relevance vector machine,RVM)算法的对手协商偏好(Preference)学习方法。在该方法中,将协商过程看作是协商议题的报价序列,把报价序列映射到新的特征空间,形成出价轨迹。用相关向量机学习出价轨迹,得到协商对手的协商偏好。以双方协商偏好为基础,通过一个优化过程产生双赢的最优反建议。实验数据表明,新方法能够减少协商回合数,增加协商总效用。

In order to further increase the precision of opponent＇s negotiation preference estimation in e-business,a relevance vector machine based method is proposed to learn opponent＇s negotiation preference. The process of negotiation is viewed as a proposal＇s sequence which can be mapped into bidding trajectory feature space. The opponent＇s preference of each issue can be learnt from bidding trajectory. Based on the negotiation preference, win-win negotiation counter proposal is generated through an optimization process. Experimental results show that the new method can decrease negotiation rounds and increase total negotiation utility.