Financial Crisis Prediction in Chinese Real Estate Industry from Cash Flow Perspective Based on Machine Learning

This paper is aims to establish a financial crisis prediction model in real estate industry. The data was acquired from financial statements of 125 listed real estate companies in China from 2013 to 2017 and listed companies marked with ST or ST* are regarded as enterprises in financial crisis. Since the financial crisis of Chinese real estate enterprises is mostly due to the rupture of cash flow chain and inability to repay debts, as a result, 18 features are selected from four dimensions of operational risk, investment risk, financing risk and capital chain risk based on cash flow perspective. This paper imputes the missing values by K-nearest Neighbor (KNN) imputation method and oversampling for imbalanced dataset using Synthetic Minority Oversampling Technique (SMOTE) method. After that, Light Gradient Boosting Machine (LightGBM) algorithm is used to establish financial crisis prediction model, and the accuracy of the model reached 96%. To illustrate the key factors, this paper ranks the importance of each feature by LightGBM classifier, it can be concluded that the financing risk is very important for enterprises into financial crisis and the project investment in the real estate industry should be treated with more caution. This paper innovatively uses method of machine learning to establish financial crisis prediction model for the real estate industry by cash flow features, which is more in line with the actual situation of the real estate industry.