财务困境概率贝叶斯估计

The Prediction of the Probability of Financial Distress:a Bayesian Model

通过财务困境概率估计模型建立一套企业财务风险预测系统,具有降低企业经营风险、投资风险以及防范金融危机的重要意义。现有的预测模型主要有:多元识别分析模型、Logit和Probit等统计回归模型以及人工神经网络预测模型。但以上模型均忽略了决策者个人经验、智慧以及信息优势对财务困境预测的重要作用。本文利用贝叶斯分析方法建立的概率估计模型,可以较好地解决这个问题,提高预测的针对性和准确性。

To build up a warning system of enterprise's financial risk using the estimated probability of financial distress is indispensable in reducing firm's operation and investment risk,and preventing national finance crisis. The traditional prediction models, no matter they are Discriminant Analysis Model, Logit Regression Model, or Article Neural Network Model, all analyze a firm's financial status according to the firm's current financial index. Firm-specific factors, macroeconomic trend, and industrial factor are omitted from the model, as well as decision-maker's individual influence from experience, wisdom and information priority. In order to better handle this problem and improve the accuracy of the model, this article developed a Bayesian model to predict the failure of company using decision-maker's individual judgment.