Font Size: a A A

Can The Random Forest Model Predict Bond Default In China?

Posted on:2021-02-06Degree:MasterType:Thesis
Country:ChinaCandidate:Y R DaiFull Text:PDF
GTID:2480306017455674Subject:Investment
Abstract/Summary:PDF Full Text Request
In 2014 China had first bond default.Since then,there are more and more bond default in China.Especially the year 2018.This has a very bad effect on investors and the whole market.On the one hand,there are few papers about predicting models of bond default that use random forest model;on the other hand,Chinese economy has its characteristics,implicit government guarantee has great impact on bond market,which let the market have the expectation of rigid payment of bonds,and enterprises continue to issue bonds and expand.When China's economic growth slows down,the implicit guarantee ability of local governments declines,the rigid payment is broken,the capital chain of enterprises is tense,and the default of corporate bonds is constantly emerging.In this paper,I collected 87 bond default companies and 870 companies which have not defaulted from 2014 to May 2019.As for the financial indexes,I used lag two dataset.Then I chose the random forest model which is representative in machine learning methods to predict bond default.And I also used cosset logit model and panel logit model to compare their predicting ability with random forest model.Empirical results show that machine learning methods can predict bond default efficiently,random forest model has high accuracy in predicting bond default.Insample training,the accuracy of random forest is 99.45%.When on out-sample test,the accuracy of random forest is 94.84%.Whether on in-sample training or on out-sample test,the accuracy of random forest is higher than cosset logit model.This shows random forest model can be used to predict bond default and it can play a very important role.And in this paper,we find that the coefficient of index implicit government guarantee is negative,and significant at 1%level.This shows company bond default risk and implicit government guarantee are negative correlation.When the implicit government guarantee ability is strong,the risk of company bond default is lower.When the implicit government guarantee ability is weak,company bond default risk is higher.At the same time,this is an indirect explanation that there is relationship between company bond default risk and macroeconomic.And over investment is positive coefficient with bond default and significant at 5%level.
Keywords/Search Tags:Bond default, Random forest model, Implicit government guarantee
PDF Full Text Request
Related items