Research On Forecasting Of Financial Crisis By Using The Average Regulation Based Period Gene

With the significant development of Chinese economy as well as the financialtrade, more attention has been attracted to the forecasting of financial crisis. Based onthe lessons learned from lots of fraudulent financial practices, it has been recognizedthat the investigation on forecasting of financial crisis is always of significance toreduce the Financial and economic risks. It is considered that all the participants,including the stockholders, creditors, senior management and auditors, will definitelybenefit from the predicting corporate failure, which usually is premised on theproperly formulated predicting methods and the accurate analysis result should makepeople have right choices.Various different methods has been applied in the field of predicting financedistress, including statistical analysis, neural network technologies, genetic algorithm,logistic analysis etc. Although these classical methods have good performance in theprediction of financial distress, there still exist some other disadvantages. As financialdata should be panel ones, most investigations only focus on one year’s financial datato interpret the underlying statistic model, which hence may fail to characterize thebusiness failure tendency of ST companies. In comparison, panel data combinescross-section data with time series data so that it can provide researcher with a hugeamount of data as well as multi-dimension perspectives.By utilizing panel data based on the binary gene expressions, this article aims atconstructing a dynamic prediction model which can explore multiple years’ financialdata. By resorting to the dynamic thresholding techniques, the marginal value duringdiscretization can be properly derived by a relative floating on the correspondingindustry average value. Relying on the discrete expression, the period gene can beidentified from the provided time binary sequence, which can be then explored torecognize ST company. Numerical simulation has demonstrated that our new methodcan significantly improve the prediction accuracy of realistic financial data, which isof great significance to both theoretical analysis and realistic applications.