Financial early warning research in the blockchain industry based on factor analysis and logistic regression model

Despite the rapid development of blockchain technology, it also brings significant and unpredictable risks. This paper mainly analyzes the financial data of 47 blockchain companies to predict their financial risks. Through extensive literature research and the unique characteristics of blockchain financial data, this paper finally identifies 18 key financial indicators, covering the solvency and operational efficiency After conducting normality and T-test or J-T test on these indicators, 10 indicators that can best predict financial risk are selected. In order to better reduce the error of logistic regression, this paper uses factor analysis to reduce dimension and extracts three main common factors according to their contribution to variation These factors are used as independent variables in the binary logistic regression model, the presence of financial risk (ST company code 1, non-ST code 0) as the dependent variable, and the financial early warning model based on this model achieved an accuracy of about 90%, indicating its high efficiency in predicting financial risks within the blockchain domain suggesting its high effectiveness in predicting financial risks within the blockchain sector.