Abstract Corporate financial distress prediction is the critical importance for decision making of managers, investors and shareholders. In current financial distress prediction models, various financial ratios are and non-financial ratio usually selected as prediction variables, which implicates that these financial ratios and non-financial ratio represent the possible cause of financial distress. In this paper, we propose a financial distress prediction model using efficiency as a predictor variable. The author collected financial distress firms in Taiwan electronic industry during 2004 to 2008. We use the data of corporations listed in Taiwan stock exchange (TSE). Experimental results of the two main financial distress prediction models, i.e., logistic regression, Neural Network (NN). In this research, the model structured by neural network model is better than the one structured by logistic regression.