基于随机森林和SVM算法的信息技术企业财务困境预测

Financial distress prediction of information technology companies based on random forest and SVM model

信息技术企业在快速发展的同时,面临激烈的市场竞争与高度的不确定性,近年来,不断有信息技术上市企业陷入财务困境,因此信息技术上市企业的财务困境预测对于投资者、企业和市场监管部门等十分重要。采用随机森林与支持向量机(SVM)两种机器学习算法,以A股上市的信息技术企业为例对样本公司在T年的财务困境情况进行了研究,并利用算法的评价指标对各个模型在不同时期的预测结果进行比较。研究结果表明,在同一数据集上的两种模型都具有较高的准确率,而SVM模型的预测效果要优于随机森林模型,并且越靠近T年,两个模型的预测效果越好。

With the rapid development of information technology companies,they face fierce market competition and high un-certainty.In recent years,there are constantly listed information technology companies falling into financial distress.Therefore,it is very important for investors,companies and market supervision administration to predict the financial distress of listed information technology companies.By using two machine learning algorithms,random forest and support vector machine(SVM),the research takes A-share listed information technology companies as an example to predict the financial distress of the sample companies in the year T,and uses relevant evaluation indicators to cross-compare the prediction effects of each model in different periods.The results show that the above two models which built on the same datasets can predict the financial situation in the T-year with higher accuracy,while the prediction effect of the SVM model is better than that of the random forest,and the closer to the T-year,the bet-ter the prediction effect of the two models will be.