In this paper, we first survey the relative literatures to find the financial indicators. And then we use the methods of DEA-DA、neural network and logistic regression by the financial indicators to establish the prediction models of financial distress. In the main results, we discover that the hit rates of these three models are at least 80%. Furthermore, the sensitivity is 33.3% and the specificity is 100% for the logistic regression model. The sensitivity is more than 60% and the specificity are more than 60% and the specificity are more than 85% for the DEA-DA and neural network models.