{"title":"Analysis and Research on Enterprise Financial Information Monitoring Model","authors":"Zhiling Li, W. Tan","doi":"10.1109/ICCSMT54525.2021.00021","DOIUrl":null,"url":null,"abstract":"The financial status of a company is related to company managers and investors, and the government also needs to stabilize the economic market by formulating rules and regulations to stabilize the company as much as possible. Therefore, it is of great significance to construct an effective early warning of corporate financial crisis. In this paper, the financial data of enterprises that can reflect the market situation are collected. Meanwhile, the data are preliminarily selected, the missing values of the data are filled, and the feature selection of the data is carried out, which provides an excellent data set for the construction of the subsequent model. Moreover, in data filling part, according to previous studies on the missing value filling method, three methods with better filling effect are found by the mean square error which is used as the evaluation index to select the filling method that is more suitable for the data set in this paper, and the selected filling method is adopted to fill in missing values. In the data feature selection part, three methods, namely significance test, random forest, and Lasso, are used to select the feature variables that will eventually be included in the model. The method in this paper can find out the reason and perform adjustment in time, which will be of great significance to the company, creditors, investors and even the entire market.","PeriodicalId":304337,"journal":{"name":"2021 2nd International Conference on Computer Science and Management Technology (ICCSMT)","volume":"449 1","pages":"0"},"PeriodicalIF":0.0000,"publicationDate":"2021-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":null,"platform":"Semanticscholar","paperid":null,"PeriodicalName":"2021 2nd International Conference on Computer Science and Management Technology (ICCSMT)","FirstCategoryId":"1085","ListUrlMain":"https://doi.org/10.1109/ICCSMT54525.2021.00021","RegionNum":0,"RegionCategory":null,"ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"","JCRName":"","Score":null,"Total":0}
引用次数: 0
Abstract
The financial status of a company is related to company managers and investors, and the government also needs to stabilize the economic market by formulating rules and regulations to stabilize the company as much as possible. Therefore, it is of great significance to construct an effective early warning of corporate financial crisis. In this paper, the financial data of enterprises that can reflect the market situation are collected. Meanwhile, the data are preliminarily selected, the missing values of the data are filled, and the feature selection of the data is carried out, which provides an excellent data set for the construction of the subsequent model. Moreover, in data filling part, according to previous studies on the missing value filling method, three methods with better filling effect are found by the mean square error which is used as the evaluation index to select the filling method that is more suitable for the data set in this paper, and the selected filling method is adopted to fill in missing values. In the data feature selection part, three methods, namely significance test, random forest, and Lasso, are used to select the feature variables that will eventually be included in the model. The method in this paper can find out the reason and perform adjustment in time, which will be of great significance to the company, creditors, investors and even the entire market.