Internet Financial Credit Evaluation Based on the Fusion of GBDT and LR

DOI

10.2991/meess-18.2018.17How to use a DOI?

Keywords

Internet financial; Credit evaluation; Feature combination; the fusion of GBDT and LR.

Abstract

With the rapid development of Internet financial credit business, credit evaluation has become a hot spot in the development of the industry. Aiming at the problem of complex data type and large amount of data in original data set, an evaluation model based on Gradient Boosting Decision Tree (GBDT) and Logistic Regression (LR) fusion is proposed. LR model is a very practical model in credit evaluation. The model is simple and fast, but it has high requirement for feature processing. GBDT has natural advantages in processing multi data type data, and it can extract new features from raw data. The fusion of the two can not only fully excavate the information of the data set, but also improve the training efficiency. Compared with other models on Internet financial credit data, it has higher accuracy, recall and Score.

Copyright

© 2018, 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  - Tao Zhang
AU  - Shuo Meng
PY  - 2018/08
DA  - 2018/08
TI  - Internet Financial Credit Evaluation Based on the Fusion of GBDT and LR
BT  - Proceedings of the 2018 International Conference on Management, Economics, Education and Social Sciences (MEESS 2018)
PB  - Atlantis Press
SP  - 86
EP  - 91
SN  - 2352-5398
UR  - https://doi.org/10.2991/meess-18.2018.17
DO  - 10.2991/meess-18.2018.17
ID  - Zhang2018/08
ER  -