Boya Century Publishing

Academic
Efficient
Fast
Article Details
EEIM032.pdf
Article Title : Research on Enterprise Bankruptcy Prediction Method Based on XGBOOST Model
Author(s) : Xuanxuan Lin
Corresponding Author : Xuanxuan Lin
Keywords : Financial Companies; Enterprise Bankruptcy; XGBOOST; Feature Extraction
PDF : http://download.BCPub.org/proceedings/2021/EEIM2021/EEIM032.pdf
Abstract

Under the trend of economic globalization, financial companies are faced with loan risk all the time. This paper proposes an enterprise bankruptcy prediction method based on the XGBOOST model to avoid the risk of bankruptcy. Firstly, the XGBOOST algorithm is used in this paper to screen out important indicators. Then extract the important features according to the first twenty real financial indicators related to the company. Secondly, the selected important indicators are used to build the model. Finally, the validity of the proposed method is verified based on the data set collected from the Taiwan Economic Journal for the years 1999 to 2009. Experimental results show that compared with Logistic Regression, Decision Tree, and Support Vector Machine, eXtreme Gradient Boostinghas better performance inaccuracy, and it has important practical significance for predicting corporate bankruptcy.

Contact email:contact@bcpub.org
Journals
Proceedings