Previous studies usually only use financial variables to establish financial distress forecasting models. However, if companies have financial crises before the financial reports are revealed, investors can’t use them to establish the models. This study will use the financial data of the previous two years and add market variables to build financial distress prediction models. The results show that adding marketing variables improve the performance of the models in the majority time. Compared to other machine learning algorithms, random forest is the best model in out-of-sample tests.