View in EDS PDF Full Text

ADAPTIVE ANOMALY CORRECTION AND DYNAMIC SAMPLE BALANCING FOR DEEP INTELLIGENT CREDIT RISK ASSESSMENT FRAMEWORK.

Saved in:
Bibliographic Details
Title: ADAPTIVE ANOMALY CORRECTION AND DYNAMIC SAMPLE BALANCING FOR DEEP INTELLIGENT CREDIT RISK ASSESSMENT FRAMEWORK.
Authors: xueping, Zhu1,2 zhuxueping@um.edu.cn, Samuri, Suzani Mohamad3 msuzani@meta.upsi.edu.my, Adnan, Muhamad Hariz Muhamad4 mhariz@meta.upsi.edu.my
Source: NED University Journal of Research. 2026, Vol. 23 Issue 1, p44-69. 26p.
Subjects: Autoencoders, Adaptive sampling (Statistics), Outliers (Statistics), Credit analysis, Classification, Financial technology, Deep learning
Abstract: With the rapid development of fintech, credit risk assessment has become a critical task for financial institutions in managing loan default risks. This paper proposes an FGA-SAE model that integrates a Stacked Autoencoder (SAE) with a sample ratio adjustment algorithm, aiming to enhance classification accuracy and robustness in credit risk assessment. Experimental comparisons demonstrate that the complete FGA-SAE model exhibits superior performance in handling data imbalance and anomaly samples. Compared to models without sample ratio adjustment and anomaly sample correction, the complete FGA-SAE model achieves significantly improved classification accuracy andfaster convergence of loss values. The model effectively mitigates the impact of class imbalance on classification performance while significantly enhancing overall model performance through anomaly sample correction via the autoencoder. This study provides an innovative and efficient solution for credit risk assessment. [ABSTRACT FROM AUTHOR]
Copyright of NED University Journal of Research is the property of NED University of Engineering & Technology and its content may not be copied or emailed to multiple sites without the copyright holder's express written permission. Additionally, content may not be used with any artificial intelligence tools or machine learning technologies. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract. (Copyright applies to all Abstracts.)
Database: Engineering Source
FullText Links:
  – Type: pdflink
Text:
  Availability: 0
Header DbId: egs
DbLabel: Engineering Source
An: 192710799
AccessLevel: 6
PubType: Academic Journal
PubTypeId: academicJournal
PreciseRelevancyScore: 0
IllustrationInfo
Items – Name: Title
  Label: Title
  Group: Ti
  Data: ADAPTIVE ANOMALY CORRECTION AND DYNAMIC SAMPLE BALANCING FOR DEEP INTELLIGENT CREDIT RISK ASSESSMENT FRAMEWORK.
– Name: Author
  Label: Authors
  Group: Au
  Data: <searchLink fieldCode="AR" term="%22xueping%2C+Zhu%22">xueping, Zhu</searchLink><relatesTo>1,2</relatesTo><i> zhuxueping@um.edu.cn</i><br /><searchLink fieldCode="AR" term="%22Samuri%2C+Suzani+Mohamad%22">Samuri, Suzani Mohamad</searchLink><relatesTo>3</relatesTo><i> msuzani@meta.upsi.edu.my</i><br /><searchLink fieldCode="AR" term="%22Adnan%2C+Muhamad+Hariz+Muhamad%22">Adnan, Muhamad Hariz Muhamad</searchLink><relatesTo>4</relatesTo><i> mhariz@meta.upsi.edu.my</i>
– Name: TitleSource
  Label: Source
  Group: Src
  Data: <searchLink fieldCode="JN" term="%22NED+University+Journal+of+Research%22">NED University Journal of Research</searchLink>. 2026, Vol. 23 Issue 1, p44-69. 26p.
– Name: Subject
  Label: Subjects
  Group: Su
  Data: <searchLink fieldCode="DE" term="%22Autoencoders%22">Autoencoders</searchLink><br /><searchLink fieldCode="DE" term="%22Adaptive+sampling+%28Statistics%29%22">Adaptive sampling (Statistics)</searchLink><br /><searchLink fieldCode="DE" term="%22Outliers+%28Statistics%29%22">Outliers (Statistics)</searchLink><br /><searchLink fieldCode="DE" term="%22Credit+analysis%22">Credit analysis</searchLink><br /><searchLink fieldCode="DE" term="%22Classification%22">Classification</searchLink><br /><searchLink fieldCode="DE" term="%22Financial+technology%22">Financial technology</searchLink><br /><searchLink fieldCode="DE" term="%22Deep+learning%22">Deep learning</searchLink>
– Name: Abstract
  Label: Abstract
  Group: Ab
  Data: With the rapid development of fintech, credit risk assessment has become a critical task for financial institutions in managing loan default risks. This paper proposes an FGA-SAE model that integrates a Stacked Autoencoder (SAE) with a sample ratio adjustment algorithm, aiming to enhance classification accuracy and robustness in credit risk assessment. Experimental comparisons demonstrate that the complete FGA-SAE model exhibits superior performance in handling data imbalance and anomaly samples. Compared to models without sample ratio adjustment and anomaly sample correction, the complete FGA-SAE model achieves significantly improved classification accuracy andfaster convergence of loss values. The model effectively mitigates the impact of class imbalance on classification performance while significantly enhancing overall model performance through anomaly sample correction via the autoencoder. This study provides an innovative and efficient solution for credit risk assessment. [ABSTRACT FROM AUTHOR]
– Name: AbstractSuppliedCopyright
  Label:
  Group: Ab
  Data: <i>Copyright of NED University Journal of Research is the property of NED University of Engineering & Technology and its content may not be copied or emailed to multiple sites without the copyright holder's express written permission. Additionally, content may not be used with any artificial intelligence tools or machine learning technologies. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract.</i> (Copyright applies to all Abstracts.)
PLink https://search.ebscohost.com/login.aspx?direct=true&site=eds-live&db=egs&AN=192710799
RecordInfo BibRecord:
  BibEntity:
    Identifiers:
      – Type: doi
        Value: 10.35453/NEDJR-ASCN-2025-007.R4
    Languages:
      – Code: eng
        Text: English
    PhysicalDescription:
      Pagination:
        PageCount: 26
        StartPage: 44
    Subjects:
      – SubjectFull: Autoencoders
        Type: general
      – SubjectFull: Adaptive sampling (Statistics)
        Type: general
      – SubjectFull: Outliers (Statistics)
        Type: general
      – SubjectFull: Credit analysis
        Type: general
      – SubjectFull: Classification
        Type: general
      – SubjectFull: Financial technology
        Type: general
      – SubjectFull: Deep learning
        Type: general
    Titles:
      – TitleFull: ADAPTIVE ANOMALY CORRECTION AND DYNAMIC SAMPLE BALANCING FOR DEEP INTELLIGENT CREDIT RISK ASSESSMENT FRAMEWORK.
        Type: main
  BibRelationships:
    HasContributorRelationships:
      – PersonEntity:
          Name:
            NameFull: xueping, Zhu
      – PersonEntity:
          Name:
            NameFull: Samuri, Suzani Mohamad
      – PersonEntity:
          Name:
            NameFull: Adnan, Muhamad Hariz Muhamad
    IsPartOfRelationships:
      – BibEntity:
          Dates:
            – D: 01
              M: 01
              Text: 2026
              Type: published
              Y: 2026
          Identifiers:
            – Type: issn-print
              Value: 2304716X
          Numbering:
            – Type: volume
              Value: 23
            – Type: issue
              Value: 1
          Titles:
            – TitleFull: NED University Journal of Research
              Type: main
ResultId 1