随机森林模型是近十年数据挖掘组合分类技术中的前沿问题,目前已在多个领域得到广泛应用。文章利用随机森林方法法建立了基于随机森林分类算法的我国上市公司财务失败预警模型,通过与逻辑回归模型、SVM支持向量机模型、CART分类树模型和神经网络模型的预测结果的对比表明随机森林模型的预测精度更高,稳健性更好,可以更好地提高我国上市公司的抗风险能力。 Stochastic forest model is a frontier problem in data mining combined taxonomy for nearly ten years and has been widely used in many fields at present. In this paper, a random forest method is used to establish the financial failure prediction model of Chinese listed companies based on stochastic forest classification algorithm. Comparing with the prediction results of logistic regression model, SVM support vector machine model, CART classification tree model and neural network model, The prediction accuracy of the model is higher and its robustness is better, which can better improve the anti-risk ability of listed companies in our country.