Assessment Methods of Credit Risk of Agencies Based on Web Data

DOI

10.2991/msmi-16.2016.89How to use a DOI?

Keywords

Credit risk assessment, Web data, Sentiment analysis, Sentence tendency analysis.

Abstract

Most of the existing studies in credit risk assessment of agencies are based on financial data, on the one hand which can't fully reflect the credit status of the agencies, and on the other hand the financial data of some agencies are difficult to obtain. In order to make up for the deficiency of the traditional assessment methods, this paper attempts to utilize Web credit data to assess the credit risk of agencies. Combined with text mining technology and sentiment analysis theories, a credit risk assessment of agencies model which is based on the comprehensive calculation results of sentence sentiment tendency value and evaluation words sentiment tendency value of agencies' Web data set is proposed in this study. To test the model, we grab four agencies' Web data and utilize the model to assess the credit risk of the four agencies. The experiment results are basically in accordance with the actual credit risk status of agencies, which indicates the feasibility of the model.

Copyright

© 2016, 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  - Xin-Yu Ma
AU  - Jian-Yun Shang
AU  - Qian Zhu
AU  - Yue-Ying He
AU  - Zhong-Hua Zhao
PY  - 2016/08
DA  - 2016/08
TI  - Assessment Methods of Credit Risk of Agencies Based on Web Data
BT  - Proceedings of the 2016 International Conference on Management Science and Management Innovation
PB  - Atlantis Press
SP  - 379
EP  - 384
SN  - 2352-5428
UR  - https://doi.org/10.2991/msmi-16.2016.89
DO  - 10.2991/msmi-16.2016.89
ID  - Ma2016/08
ER  -