Analyzing financial distress of listed companies using neural network

Corporation financial distress has been an important issue for study in the financial fields. This paper uses traditional BP neural network model and proposes PNN model to predicate financial distress. The sample consists of 276 companies listed on the Shanghai Stock Exchange and Shenzhen Stock Exchange over the period 2001-2010. Factor analysis is used to lower correlation and reduce dimensionality. The results demonstrate that the PNN model has higher explanatory power in predicating financial distress than BPN model.