【摘要】 通过遗传算法结合支持向量机算法中期望风险边界,对我国上市公司财务数据进行特征提取,并优化构造广义最优分类超平面,从而获得具有较好整体预测性能的联合模型。数值实验表明,该方法可以降低特征空间维数,具有较好的分类准确率。实证结果表明,GA-SVM联合预测模型具有可靠的预测财务困境能力,有着良好的应用前景。更多还原

【Abstract】 This paper uses genetic algorithm and support vector machine to set up a hybrid model of financial distress prediction in Chinese listed firms. Numerical simulation shows that the proposed method can reduce the dimension of the feature space, and has higher correct classification rate. As the result, the proposed GA-SVM hybrid model has reliable financial distress prediction ability, and it has a good application prospect in this area.更多还原