Improved ML-Based Technique for Credit Card Scoring in Internet Financial Risk Control
With the rapid development of China’s Internet finance industry and the continuous growth of transaction amount in recent years, a variety of financial risks have increased, especially credit risk in the financial industry. Also, the credit risk evaluation is usually made by using the application ca...
Saved in:
| Main Authors: | , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Wiley
2020-01-01
|
| Series: | Complexity |
| Online Access: | http://dx.doi.org/10.1155/2020/8706285 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1832560219057553408 |
|---|---|
| author | Shuangshuang Fan Yanbo Shen Shengnan Peng |
| author_facet | Shuangshuang Fan Yanbo Shen Shengnan Peng |
| author_sort | Shuangshuang Fan |
| collection | DOAJ |
| description | With the rapid development of China’s Internet finance industry and the continuous growth of transaction amount in recent years, a variety of financial risks have increased, especially credit risk in the financial industry. Also, the credit risk evaluation is usually made by using the application card scoring model, which has the shortcomings of strict data assumption and inability to process complex data. In order to overcome the limitations of the credit card scoring model and evaluate credit risk better, this paper proposes a credit evaluation model based on extreme gradient boosting tree (XGBoost) machine learning (ML) algorithm to construct a credit risk assessment model for Internet financial institutions. At the same time, an Internet lending company in China is taken as a case study to compare the performance of the traditional credit card scoring model and the proposed machine learning (ML) algorithm model. The results show that ML algorithm has a very significant advantage in the field of Internet financial risk control, it has more accurate prediction results and has no particularly strict assumptions and restrictions on data, and the process of processing data is more convenient and reliable. We should increase the application of ML in the field of financial risk control. The value of this paper lies in enriching the related research of financial technology and providing a new reference for the practice of financial risk control. |
| format | Article |
| id | doaj-art-f43debf9d79349cea4e87eb17c5dfc63 |
| institution | Kabale University |
| issn | 1076-2787 1099-0526 |
| language | English |
| publishDate | 2020-01-01 |
| publisher | Wiley |
| record_format | Article |
| series | Complexity |
| spelling | doaj-art-f43debf9d79349cea4e87eb17c5dfc632025-02-03T01:28:14ZengWileyComplexity1076-27871099-05262020-01-01202010.1155/2020/87062858706285Improved ML-Based Technique for Credit Card Scoring in Internet Financial Risk ControlShuangshuang Fan0Yanbo Shen1Shengnan Peng2School of Management, China University of Mining and Technology-Beijing, Beijing, CO 100080, ChinaDahua Certified Public Accountants, Beijing, CO 100080, ChinaSchool of Management, China University of Mining and Technology-Beijing, Beijing, CO 100080, ChinaWith the rapid development of China’s Internet finance industry and the continuous growth of transaction amount in recent years, a variety of financial risks have increased, especially credit risk in the financial industry. Also, the credit risk evaluation is usually made by using the application card scoring model, which has the shortcomings of strict data assumption and inability to process complex data. In order to overcome the limitations of the credit card scoring model and evaluate credit risk better, this paper proposes a credit evaluation model based on extreme gradient boosting tree (XGBoost) machine learning (ML) algorithm to construct a credit risk assessment model for Internet financial institutions. At the same time, an Internet lending company in China is taken as a case study to compare the performance of the traditional credit card scoring model and the proposed machine learning (ML) algorithm model. The results show that ML algorithm has a very significant advantage in the field of Internet financial risk control, it has more accurate prediction results and has no particularly strict assumptions and restrictions on data, and the process of processing data is more convenient and reliable. We should increase the application of ML in the field of financial risk control. The value of this paper lies in enriching the related research of financial technology and providing a new reference for the practice of financial risk control.http://dx.doi.org/10.1155/2020/8706285 |
| spellingShingle | Shuangshuang Fan Yanbo Shen Shengnan Peng Improved ML-Based Technique for Credit Card Scoring in Internet Financial Risk Control Complexity |
| title | Improved ML-Based Technique for Credit Card Scoring in Internet Financial Risk Control |
| title_full | Improved ML-Based Technique for Credit Card Scoring in Internet Financial Risk Control |
| title_fullStr | Improved ML-Based Technique for Credit Card Scoring in Internet Financial Risk Control |
| title_full_unstemmed | Improved ML-Based Technique for Credit Card Scoring in Internet Financial Risk Control |
| title_short | Improved ML-Based Technique for Credit Card Scoring in Internet Financial Risk Control |
| title_sort | improved ml based technique for credit card scoring in internet financial risk control |
| url | http://dx.doi.org/10.1155/2020/8706285 |
| work_keys_str_mv | AT shuangshuangfan improvedmlbasedtechniqueforcreditcardscoringininternetfinancialriskcontrol AT yanboshen improvedmlbasedtechniqueforcreditcardscoringininternetfinancialriskcontrol AT shengnanpeng improvedmlbasedtechniqueforcreditcardscoringininternetfinancialriskcontrol |