The robustness test results of the model.
<div><p>To enhance the accuracy and response speed of the risk early warning system, this study develops a novel early warning system that combines the Fuzzy C-Means (FCM) clustering algorithm and the Random Forest (RF) model. Firstly, based on operational risk theory, market risk, resea...
Saved in:
| Main Author: | |
|---|---|
| Published: |
2025
|
| Subjects: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1852022175119179776 |
|---|---|
| author | Xini Fang (20861990) |
| author_facet | Xini Fang (20861990) |
| author_role | author |
| dc.creator.none.fl_str_mv | Xini Fang (20861990) |
| dc.date.none.fl_str_mv | 2025-03-11T17:42:06Z |
| dc.identifier.none.fl_str_mv | 10.1371/journal.pone.0318491.t003 |
| dc.relation.none.fl_str_mv | https://figshare.com/articles/dataset/The_robustness_test_results_of_the_model_/28577171 |
| dc.rights.none.fl_str_mv | CC BY 4.0 info:eu-repo/semantics/openAccess |
| dc.subject.none.fl_str_mv | Biotechnology Immunology Environmental Sciences not elsewhere classified Biological Sciences not elsewhere classified Mathematical Sciences not elsewhere classified Information Systems not elsewhere classified provides basic information experimental results show early warning strategies operational risk theory human resource risk enterprise risk assessment model &# 8217 45 %, 5 45 %, 4 09 %, 4 processing sample data handle complex data corporate operational risk traditional rf model improved rf model fcm clustering algorithm clustering algorithm rf algorithm risk indicators market risk financial risk development risk model achieves 95 %, 81 %, 29 %, 26 %, 20 %, rating data performance data fcm clustering data classification corporate bonds xlink "> weight method thereby enhancing response speed respectively 6 random forest primary indicators net value intercriteria correlation income products fuzzy c f1 score 48 %. |
| dc.title.none.fl_str_mv | The robustness test results of the model. |
| dc.type.none.fl_str_mv | Dataset info:eu-repo/semantics/publishedVersion dataset |
| description | <div><p>To enhance the accuracy and response speed of the risk early warning system, this study develops a novel early warning system that combines the Fuzzy C-Means (FCM) clustering algorithm and the Random Forest (RF) model. Firstly, based on operational risk theory, market risk, research and development risk, financial risk, and human resource risk are selected as the primary indicators for enterprise risk assessment. Secondly, the Criteria Importance Through Intercriteria Correlation (CRITIC) weight method is employed to determine the importance of these risk indicators, thereby enhancing the model’s prediction ability and stability. Following this, the FCM clustering algorithm is utilized for pre-processing sample data to improve the efficiency and accuracy of data classification. Finally, an improved RF model is constructed by optimizing the parameters of the RF algorithm. The data selected is mainly from RESSET/DB, covering the issuance, trading, and rating data of fixed-income products such as bonds, government bonds, and corporate bonds, and provides basic information, net value, position, and performance data of funds. The experimental results show that the model achieves an F1 score of 87.26%, an accuracy of 87.95%, an Area under the Curve (AUC) of 91.20%, a precision of 89.29%, and a recall of 87.48%. They are respectively 6.45%, 4.45%, 5.09%, 4.81%, and 3.83% higher than the traditional RF model. In this study, an improved RF model based on FCM clustering is successfully constructed, and the accuracy of risk early warning models and their ability to handle complex data are significantly improved.</p></div> |
| eu_rights_str_mv | openAccess |
| id | Manara_278f1fcadf428cc0cb2ef81cfcc5cece |
| identifier_str_mv | 10.1371/journal.pone.0318491.t003 |
| network_acronym_str | Manara |
| network_name_str | ManaraRepo |
| oai_identifier_str | oai:figshare.com:article/28577171 |
| publishDate | 2025 |
| repository.mail.fl_str_mv | |
| repository.name.fl_str_mv | |
| repository_id_str | |
| rights_invalid_str_mv | CC BY 4.0 |
| spelling | The robustness test results of the model.Xini Fang (20861990)BiotechnologyImmunologyEnvironmental Sciences not elsewhere classifiedBiological Sciences not elsewhere classifiedMathematical Sciences not elsewhere classifiedInformation Systems not elsewhere classifiedprovides basic informationexperimental results showearly warning strategiesoperational risk theoryhuman resource riskenterprise risk assessmentmodel &# 821745 %, 545 %, 409 %, 4processing sample datahandle complex datacorporate operational risktraditional rf modelimproved rf modelfcm clustering algorithmclustering algorithmrf algorithmrisk indicatorsmarket riskfinancial riskdevelopment riskmodel achieves95 %,81 %,29 %,26 %,20 %,rating dataperformance datafcm clusteringdata classificationcorporate bondsxlink ">weight methodthereby enhancingresponse speedrespectively 6random forestprimary indicatorsnet valueintercriteria correlationincome productsfuzzy cf1 score48 %.<div><p>To enhance the accuracy and response speed of the risk early warning system, this study develops a novel early warning system that combines the Fuzzy C-Means (FCM) clustering algorithm and the Random Forest (RF) model. Firstly, based on operational risk theory, market risk, research and development risk, financial risk, and human resource risk are selected as the primary indicators for enterprise risk assessment. Secondly, the Criteria Importance Through Intercriteria Correlation (CRITIC) weight method is employed to determine the importance of these risk indicators, thereby enhancing the model’s prediction ability and stability. Following this, the FCM clustering algorithm is utilized for pre-processing sample data to improve the efficiency and accuracy of data classification. Finally, an improved RF model is constructed by optimizing the parameters of the RF algorithm. The data selected is mainly from RESSET/DB, covering the issuance, trading, and rating data of fixed-income products such as bonds, government bonds, and corporate bonds, and provides basic information, net value, position, and performance data of funds. The experimental results show that the model achieves an F1 score of 87.26%, an accuracy of 87.95%, an Area under the Curve (AUC) of 91.20%, a precision of 89.29%, and a recall of 87.48%. They are respectively 6.45%, 4.45%, 5.09%, 4.81%, and 3.83% higher than the traditional RF model. In this study, an improved RF model based on FCM clustering is successfully constructed, and the accuracy of risk early warning models and their ability to handle complex data are significantly improved.</p></div>2025-03-11T17:42:06ZDatasetinfo:eu-repo/semantics/publishedVersiondataset10.1371/journal.pone.0318491.t003https://figshare.com/articles/dataset/The_robustness_test_results_of_the_model_/28577171CC BY 4.0info:eu-repo/semantics/openAccessoai:figshare.com:article/285771712025-03-11T17:42:06Z |
| spellingShingle | The robustness test results of the model. Xini Fang (20861990) Biotechnology Immunology Environmental Sciences not elsewhere classified Biological Sciences not elsewhere classified Mathematical Sciences not elsewhere classified Information Systems not elsewhere classified provides basic information experimental results show early warning strategies operational risk theory human resource risk enterprise risk assessment model &# 8217 45 %, 5 45 %, 4 09 %, 4 processing sample data handle complex data corporate operational risk traditional rf model improved rf model fcm clustering algorithm clustering algorithm rf algorithm risk indicators market risk financial risk development risk model achieves 95 %, 81 %, 29 %, 26 %, 20 %, rating data performance data fcm clustering data classification corporate bonds xlink "> weight method thereby enhancing response speed respectively 6 random forest primary indicators net value intercriteria correlation income products fuzzy c f1 score 48 %. |
| status_str | publishedVersion |
| title | The robustness test results of the model. |
| title_full | The robustness test results of the model. |
| title_fullStr | The robustness test results of the model. |
| title_full_unstemmed | The robustness test results of the model. |
| title_short | The robustness test results of the model. |
| title_sort | The robustness test results of the model. |
| topic | Biotechnology Immunology Environmental Sciences not elsewhere classified Biological Sciences not elsewhere classified Mathematical Sciences not elsewhere classified Information Systems not elsewhere classified provides basic information experimental results show early warning strategies operational risk theory human resource risk enterprise risk assessment model &# 8217 45 %, 5 45 %, 4 09 %, 4 processing sample data handle complex data corporate operational risk traditional rf model improved rf model fcm clustering algorithm clustering algorithm rf algorithm risk indicators market risk financial risk development risk model achieves 95 %, 81 %, 29 %, 26 %, 20 %, rating data performance data fcm clustering data classification corporate bonds xlink "> weight method thereby enhancing response speed respectively 6 random forest primary indicators net value intercriteria correlation income products fuzzy c f1 score 48 %. |