Whether a suitable partner is selected or not has a profound impact on the performance of the entire chain and the interests of all members.In order to improve the original methods of partner evaluation,we propose a theoretical evaluation model of the candidate partners based on Support Vector Regression.We construct a new index system from a new angle of view based on investigation and the existing outcomes.In addition,an empirical study has been conducted and the results show that the new model is effective and has a good ability of generalizing.So,we have provided a scientific and objective method for the managers' decision-making of the partner selection in supply chain management.