Research On Intelligent Prediction Model Of Sme Financial Crisis

In recent years,with the support of national policies,SMEs have achieved rapid development and their role in the national economy has become increasingly prominent.However,China’s current economy has entered a new normal,and the survival and development of small and medium-sized enterprises has been different from the past,and the pressure of survival has increased.There are many factors that can trigger the financial crisis of SMEs,not only financial factors,but also non-financial factors and external macroeconomic factors.Therefore,under the new normal of the economic situation,how SMEs can resist risks and improve their ability to cope with crises has become a new focus of scholars from all walks of life.On this basis,this paper focuses on the theme of “Intelligent Forecast of SMEs’ Financial Crisis”,and uses financial information,non-financial information and public macro information to construct an intelligent information forecasting model for SME financial crisis.There are four main problems to be solved in this paper: first,the selection of distressed enterprise samples;second,the selection of matching healthy enterprise samples;third,screening variables;fourth,constructing a predictive model of financial crisis.details as follows:This paper selects ST or ST* enterprises in the small and medium-sized listed companies in 2013-2017 as the research object.Considering that there are not many such enterprises,only 40 companies with STs will be in the same industry in the past five years,and the assets will be similar.The principle selects 40 matching health companies to add samples,and then randomly selects 20 healthy companies as supplementary samples from the remaining enterprises,and a total of 100 samples for empirical research.Based on the characteristics of small and medium-sized enterprises,this paper not only considers financial information indicators,but also includes non-financial information indicators and public macro information indicators.The research shows that the addition of non-financial information data and public macro information data makes the SME financial crisis prediction index system more comprehensive and improves the prediction effect of the model.Based on the comparative analysis of the financial data,non-financial data andpublic macro information data of SMEs in SMEs,the intelligent information prediction model represented by SVM model and the traditional prediction represented by Logistic model are constructed respectively.model.In this way,managers of SMEs are encouraged to discover abnormalities in business management activities and respond to market operational risks in a timely manner.The empirical results show that the crisis prediction effect of the intelligent prediction model is significantly better than that of the traditional model,and the prediction accuracy is as high as 90%.It can better predict T+2 years based on financial data,non-financial data and public macro information data.Whether SMEs will fall into financial crisis is of practical significance.All in all,based on the characteristics of SMEs’ own development,this paper comprehensively considers the non-financial information indicators and public macro information indicators in the original financial information-based forecasting index system,and builds the financial crisis of SMEs represented by SVM.Intelligent information prediction model.This model provides technical support for managers to prevent financial crisis and control the business risks of enterprises,and has practical value.