Abstract: This paper studies performance evaluation of supply chain based on Genetic Algorithm（GA） and Support Vector Machine（SVM）.A simultaneous feature selection and SVM parameter optimization algorithm based on GA is used to solve the performance evaluation problem of supply chain.The study shows that important attributes that influence the performance of supply chain are extracted and the complexity of the performance evaluation model of the supply chain is reduced.The numerical exam-ple demonstrates that the result of the performance evaluation of supply chain based on GA and SVM is superior to standard SVM.

Key words: supply chain, performance evaluation, Support Vector Machine（SVM）, Genetic Algorithm（GA）, feature selection

摘要： 研究了基于遗传算法和支持向量机的供应链绩效评价问题。将供应链绩效评价问题用遗传算法进行特征选择并同时对支持向量机参数进行了优化。研究表明该方法能提取出影响供应链绩效的重要属性，减小供应链评价模型的复杂度。应用实例表明基于遗传算法和支持向量机的评价结果从整体上要优于标准支持向量机的评价结果。

关键词: 供应链, 绩效评价, 支持向量机（SVM）, 遗传算法（GA）, 特征选择