Research on the Application of Data Mining In the Financial Risk Early Warning of Listing Corporation

DOI

10.2991/isss-17.2017.109How to use a DOI?

Keywords

CRISP-DM, Data mining; Logistic regression, Support Vector Machine, Decision tree, Neural network, The financial risk warning.

Abstract

Based on the CRISP-DM process, studied the data mining Logistic regression, support vector machines, decision trees, neural network model and their application in the financial risk early warning of listed Companies. According to four models can predict the response rate and chose Logistic regression as the final model of data mining, and in accordance with the actual situation of Chinese listed companies to build the financial early warning system. By choosing the electronics industry listed companies as samples, based on the financial data of normal listed companies and ST companies, and conducting experiments to evaluate the model, the results show that: in the CRISP-DM process, based on Logistic regression data mining technology to establish financial risk prediction model, predicting the correct rate and response rate more than 85%,the stability of the model is higher, and verify the effectiveness of the data mining technology in the financial risk warning.

Copyright

© 2017, the Authors. Published by Atlantis Press.

Open Access

This is an open access article distributed under the CC BY-NC license (http://creativecommons.org/licenses/by-nc/4.0/).

Download article (PDF)

TY  - CONF
AU  - Lin Wang
AU  - Ying Liu
PY  - 2017/05
DA  - 2017/05
TI  - Research on the Application of Data Mining In the Financial Risk Early Warning of Listing Corporation
BT  - Proceedings of 3rd International Symposium on Social Science (ISSS 2017)
PB  - Atlantis Press
SP  - 495
EP  - 499
SN  - 2352-5398
UR  - https://doi.org/10.2991/isss-17.2017.109
DO  - 10.2991/isss-17.2017.109
ID  - Wang2017/05
ER  -