针对当前大部分企业危机预警模型特征选取和等级分类困难的现状,提出一种基于熵的预警方法.该方法首先对企业运营的指标进行特征选择,在选定指标的基础上利用判别熵选取企业危机预警特征值,然后利用熵聚类算法对预测结果进行分类,判断企业的危机状态,最后采集沪深A股上市公司的年报数据对该模型进行了实证分析,结果表明该模型有效可行. Aiming at the status quo of the current crisis early warning model feature selection and hierarchical classification difficulty in most enterprises, this paper proposes an early warning method based on entropy. This method firstly selects the features of the indexes of business operations and selects the enterprises based on the selected indexes Then use the entropy clustering algorithm to classify the prediction results to judge the state of the enterprise crisis. Finally, the annual report data of Shanghai and Shenzhen A-share listed companies are collected to make an empirical analysis of the model. The results show that the model is effective and feasible.