{"title":"基于Logistic回归和BP神经网络的大数据企业财务预警研究","authors":"Hongmei Zhang, Jian He","doi":"10.2991/dramclr-19.2019.16","DOIUrl":null,"url":null,"abstract":"—Based on the difference between big data enterprises and traditional enterprises, this paper first constructs two single financial risk early warning models: logistic regression model and BP neural network model, then introduces default probability of logistic regression model output into BP neural network model, and establishes a nonlinear combination based on BP neural network model. A new forecasting method is proposed, and an early warning model of financial crisis for large data enterprises is constructed and an empirical study is carried out. The results show that, compared with single model, the combined forecasting model has no significant improvement in the forecasting accuracy of financial early warning for large data enterprises, but the combined forecasting model is more stable. This provides a new idea for the financial risk early warning research of large data enterprises in China. Key words— combination forecasting model, large data enterprises,financial early warning 摘要—基于大数据企业与传统企业的差异,本文首先构建 了 logistic 回归模型和 BP 神经网络模型两个单一的财务风险 预警模型,然后将 logistic 回归模型输出的违约概率引入到 BP 神经网络模型中,建立了基于 BP 神经网络模型非线性组合 的预测新方法,构建了大数据企业财务危机预警模型并进行了 实证研究。结果表明,复合预测模型在对大数据企业财务预警 的预测精度上,与单一模型相比,预测精度没有显著提高,但 复合预测模型更具有稳定性。这为我国大数据企业财务风险预 警研究提供了新思路。 关键词—复合预测模型;大数据企业;财务预警","PeriodicalId":142201,"journal":{"name":"Proceedings of the Fourth Symposium on Disaster Risk Analysis and Management in Chinese Littoral Regions (DRAMCLR 2019)","volume":"278 1","pages":"0"},"PeriodicalIF":0.0000,"publicationDate":"2019-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":"{\"title\":\"Research on Financial Early Warning of Big Data Enterprises Based on Logistic Regression and BP Neural Network\",\"authors\":\"Hongmei Zhang, Jian He\",\"doi\":\"10.2991/dramclr-19.2019.16\",\"DOIUrl\":null,\"url\":null,\"abstract\":\"—Based on the difference between big data enterprises and traditional enterprises, this paper first constructs two single financial risk early warning models: logistic regression model and BP neural network model, then introduces default probability of logistic regression model output into BP neural network model, and establishes a nonlinear combination based on BP neural network model. A new forecasting method is proposed, and an early warning model of financial crisis for large data enterprises is constructed and an empirical study is carried out. The results show that, compared with single model, the combined forecasting model has no significant improvement in the forecasting accuracy of financial early warning for large data enterprises, but the combined forecasting model is more stable. This provides a new idea for the financial risk early warning research of large data enterprises in China. Key words— combination forecasting model, large data enterprises,financial early warning 摘要—基于大数据企业与传统企业的差异,本文首先构建 了 logistic 回归模型和 BP 神经网络模型两个单一的财务风险 预警模型,然后将 logistic 回归模型输出的违约概率引入到 BP 神经网络模型中,建立了基于 BP 神经网络模型非线性组合 的预测新方法,构建了大数据企业财务危机预警模型并进行了 实证研究。结果表明,复合预测模型在对大数据企业财务预警 的预测精度上,与单一模型相比,预测精度没有显著提高,但 复合预测模型更具有稳定性。这为我国大数据企业财务风险预 警研究提供了新思路。 关键词—复合预测模型;大数据企业;财务预警\",\"PeriodicalId\":142201,\"journal\":{\"name\":\"Proceedings of the Fourth Symposium on Disaster Risk Analysis and Management in Chinese Littoral Regions (DRAMCLR 2019)\",\"volume\":\"278 1\",\"pages\":\"0\"},\"PeriodicalIF\":0.0000,\"publicationDate\":\"2019-11-01\",\"publicationTypes\":\"Journal Article\",\"fieldsOfStudy\":null,\"isOpenAccess\":false,\"openAccessPdf\":\"\",\"citationCount\":\"0\",\"resultStr\":null,\"platform\":\"Semanticscholar\",\"paperid\":null,\"PeriodicalName\":\"Proceedings of the Fourth Symposium on Disaster Risk Analysis and Management in Chinese Littoral Regions (DRAMCLR 2019)\",\"FirstCategoryId\":\"1085\",\"ListUrlMain\":\"https://doi.org/10.2991/dramclr-19.2019.16\",\"RegionNum\":0,\"RegionCategory\":null,\"ArticlePicture\":[],\"TitleCN\":null,\"AbstractTextCN\":null,\"PMCID\":null,\"EPubDate\":\"\",\"PubModel\":\"\",\"JCR\":\"\",\"JCRName\":\"\",\"Score\":null,\"Total\":0}","platform":"Semanticscholar","paperid":null,"PeriodicalName":"Proceedings of the Fourth Symposium on Disaster Risk Analysis and Management in Chinese Littoral Regions (DRAMCLR 2019)","FirstCategoryId":"1085","ListUrlMain":"https://doi.org/10.2991/dramclr-19.2019.16","RegionNum":0,"RegionCategory":null,"ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"","JCRName":"","Score":null,"Total":0}
Research on Financial Early Warning of Big Data Enterprises Based on Logistic Regression and BP Neural Network
—Based on the difference between big data enterprises and traditional enterprises, this paper first constructs two single financial risk early warning models: logistic regression model and BP neural network model, then introduces default probability of logistic regression model output into BP neural network model, and establishes a nonlinear combination based on BP neural network model. A new forecasting method is proposed, and an early warning model of financial crisis for large data enterprises is constructed and an empirical study is carried out. The results show that, compared with single model, the combined forecasting model has no significant improvement in the forecasting accuracy of financial early warning for large data enterprises, but the combined forecasting model is more stable. This provides a new idea for the financial risk early warning research of large data enterprises in China. Key words— combination forecasting model, large data enterprises,financial early warning 摘要—基于大数据企业与传统企业的差异,本文首先构建 了 logistic 回归模型和 BP 神经网络模型两个单一的财务风险 预警模型,然后将 logistic 回归模型输出的违约概率引入到 BP 神经网络模型中,建立了基于 BP 神经网络模型非线性组合 的预测新方法,构建了大数据企业财务危机预警模型并进行了 实证研究。结果表明,复合预测模型在对大数据企业财务预警 的预测精度上,与单一模型相比,预测精度没有显著提高,但 复合预测模型更具有稳定性。这为我国大数据企业财务风险预 警研究提供了新思路。 关键词—复合预测模型;大数据企业;财务预警