According to Shiga University, the indicators of the bankruptcy number prediction model are business conditions, profitability, fixed cost burden, quantitative aspect of borrowing environment, interest rate aspect of borrowing environment, and external competitiveness environment.When multiple explanatory variables representing these six indicators are selected based on the amount of information, the BOJ Tankan's business conditions and selling price judgment index-purchase price judgment index, quantitative aspects of the borrowing environment, loan contract average interest rate, and real effective exchange rate Is selected, and highly predictive results are obtained.

　In order to reduce the influence of outliers that distort the parameter estimates of the model, robust estimation is performed so that even if there is a deviation from the assumption, it is not so affected, and appropriate parameter values ​​are obtained.

　When the number of bankruptcies in Corona was predicted using the bankruptcy forecast model, it was predicted that the number of bankruptcies in the fourth quarter of 2020 and the first quarter of 4 would be lower than at the time of the global financial crisis.

　Even at the upper limit of the forecast, it is at the level of the fourth quarter of 2013 to the third quarter of 4, and the decrease in the average contracted interest rate on loans and the depreciation of the real effective exchange rate will contribute to the reduction of the number of bankruptcies compared to the time of the global financial crisis. It is supposed to be.

reference:[Shiga University] Developed a model for predicting the number of bankruptcies of Corona (PDF)