View in EDS HTML Full Text PDF Full Text

Defaulter detection based on Spearman correlation with hyper tuned SVM classification for preventing non-performing assets occurring in bank.

Saved in:
Bibliographic Details
Title: Defaulter detection based on Spearman correlation with hyper tuned SVM classification for preventing non-performing assets occurring in bank.
Authors: Mallik, Rajib1 (AUTHOR) rajibmallikdr@gmail.com, Puri, Shalini2 (AUTHOR), Bhansali, Ashok3 (AUTHOR), Manikandan, R.4 (AUTHOR), Rahunathan, L.5 (AUTHOR)
Source: Multimedia Tools & Applications. Aug2025, Vol. 84 Issue 27, p33071-33093. 23p.
Subjects: Rank correlation (Statistics), Support vector machines, Banking industry, Model validation, Nonperforming loans, Counterparty risk, Feature selection
Abstract: A common problem in the banking industry is loan default prediction, which may help identify defaulters who are most likely to stop making payments on their loan payments. Additionally, this information may be used to change the terms and conditions of loans, set aside additional money to guard against potential losses, or even refuse or restrict loans to clients that present a high risk. Although there are numerous conventional techniques for extracting data from loan applications, the majority of these techniques appear to be underperforming, which results in numerous problematic loans. In this proposed model, the detection of defaulter based on Spearman rank correlation with hyper tuned SVM classification is designed for preventing non-performing assets occurring in the bank. For novelty of the model, the missing value replacement is done with the Classification and Regression Tree (CART), which is an imputation as well as classification model that can impute values at missing column based on replacing the different values place at missing place by attaining the best classification accuracy. Then the Z-score normalization and Spearman rank correlation coefficient has been used for normalizing the data and correlation based feature reduction helps to classify then model with low computational complexity. In this hyper tuned SVM model, the traditional SVM model based on grid search cross validation is used for tuning the SVM parameters to accurately detect the defaulter from preventing the non-performing assets occurring in the bank. For evaluating the performance of the proposed loan prediction model, the precision, specificity, accuracy, recall, and Error are 95%, 97%, 96%, 96% and 4%. According to this evaluations, the proposed design performs better than existing model. Thus, the loan defaulter detection using Spearman's correlation and hyper tuned SVM classification prevents the Non-Performing Assets (NPA) occurring in the bank. [ABSTRACT FROM AUTHOR]
Copyright of Multimedia Tools & Applications is the property of Springer Nature 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
Full text is not displayed to guests.
FullText Links:
  – Type: pdflink
Text:
  Availability: 1
Header DbId: egs
DbLabel: Engineering Source
An: 187118467
AccessLevel: 6
PubType: Academic Journal
PubTypeId: academicJournal
PreciseRelevancyScore: 0
IllustrationInfo
Items – Name: Title
  Label: Title
  Group: Ti
  Data: Defaulter detection based on Spearman correlation with hyper tuned SVM classification for preventing non-performing assets occurring in bank.
– Name: Author
  Label: Authors
  Group: Au
  Data: <searchLink fieldCode="AR" term="%22Mallik%2C+Rajib%22">Mallik, Rajib</searchLink><relatesTo>1</relatesTo> (AUTHOR)<i> rajibmallikdr@gmail.com</i><br /><searchLink fieldCode="AR" term="%22Puri%2C+Shalini%22">Puri, Shalini</searchLink><relatesTo>2</relatesTo> (AUTHOR)<br /><searchLink fieldCode="AR" term="%22Bhansali%2C+Ashok%22">Bhansali, Ashok</searchLink><relatesTo>3</relatesTo> (AUTHOR)<br /><searchLink fieldCode="AR" term="%22Manikandan%2C+R%2E%22">Manikandan, R.</searchLink><relatesTo>4</relatesTo> (AUTHOR)<br /><searchLink fieldCode="AR" term="%22Rahunathan%2C+L%2E%22">Rahunathan, L.</searchLink><relatesTo>5</relatesTo> (AUTHOR)
– Name: TitleSource
  Label: Source
  Group: Src
  Data: <searchLink fieldCode="JN" term="%22Multimedia+Tools+%26+Applications%22">Multimedia Tools & Applications</searchLink>. Aug2025, Vol. 84 Issue 27, p33071-33093. 23p.
– Name: Subject
  Label: Subjects
  Group: Su
  Data: <searchLink fieldCode="DE" term="%22Rank+correlation+%28Statistics%29%22">Rank correlation (Statistics)</searchLink><br /><searchLink fieldCode="DE" term="%22Support+vector+machines%22">Support vector machines</searchLink><br /><searchLink fieldCode="DE" term="%22Banking+industry%22">Banking industry</searchLink><br /><searchLink fieldCode="DE" term="%22Model+validation%22">Model validation</searchLink><br /><searchLink fieldCode="DE" term="%22Nonperforming+loans%22">Nonperforming loans</searchLink><br /><searchLink fieldCode="DE" term="%22Counterparty+risk%22">Counterparty risk</searchLink><br /><searchLink fieldCode="DE" term="%22Feature+selection%22">Feature selection</searchLink>
– Name: Abstract
  Label: Abstract
  Group: Ab
  Data: A common problem in the banking industry is loan default prediction, which may help identify defaulters who are most likely to stop making payments on their loan payments. Additionally, this information may be used to change the terms and conditions of loans, set aside additional money to guard against potential losses, or even refuse or restrict loans to clients that present a high risk. Although there are numerous conventional techniques for extracting data from loan applications, the majority of these techniques appear to be underperforming, which results in numerous problematic loans. In this proposed model, the detection of defaulter based on Spearman rank correlation with hyper tuned SVM classification is designed for preventing non-performing assets occurring in the bank. For novelty of the model, the missing value replacement is done with the Classification and Regression Tree (CART), which is an imputation as well as classification model that can impute values at missing column based on replacing the different values place at missing place by attaining the best classification accuracy. Then the Z-score normalization and Spearman rank correlation coefficient has been used for normalizing the data and correlation based feature reduction helps to classify then model with low computational complexity. In this hyper tuned SVM model, the traditional SVM model based on grid search cross validation is used for tuning the SVM parameters to accurately detect the defaulter from preventing the non-performing assets occurring in the bank. For evaluating the performance of the proposed loan prediction model, the precision, specificity, accuracy, recall, and Error are 95%, 97%, 96%, 96% and 4%. According to this evaluations, the proposed design performs better than existing model. Thus, the loan defaulter detection using Spearman's correlation and hyper tuned SVM classification prevents the Non-Performing Assets (NPA) occurring in the bank. [ABSTRACT FROM AUTHOR]
– Name: AbstractSuppliedCopyright
  Label:
  Group: Ab
  Data: <i>Copyright of Multimedia Tools & Applications is the property of Springer Nature 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=187118467
RecordInfo BibRecord:
  BibEntity:
    Identifiers:
      – Type: doi
        Value: 10.1007/s11042-024-20494-3
    Languages:
      – Code: eng
        Text: English
    PhysicalDescription:
      Pagination:
        PageCount: 23
        StartPage: 33071
    Subjects:
      – SubjectFull: Rank correlation (Statistics)
        Type: general
      – SubjectFull: Support vector machines
        Type: general
      – SubjectFull: Banking industry
        Type: general
      – SubjectFull: Model validation
        Type: general
      – SubjectFull: Nonperforming loans
        Type: general
      – SubjectFull: Counterparty risk
        Type: general
      – SubjectFull: Feature selection
        Type: general
    Titles:
      – TitleFull: Defaulter detection based on Spearman correlation with hyper tuned SVM classification for preventing non-performing assets occurring in bank.
        Type: main
  BibRelationships:
    HasContributorRelationships:
      – PersonEntity:
          Name:
            NameFull: Mallik, Rajib
      – PersonEntity:
          Name:
            NameFull: Puri, Shalini
      – PersonEntity:
          Name:
            NameFull: Bhansali, Ashok
      – PersonEntity:
          Name:
            NameFull: Manikandan, R.
      – PersonEntity:
          Name:
            NameFull: Rahunathan, L.
    IsPartOfRelationships:
      – BibEntity:
          Dates:
            – D: 21
              M: 08
              Text: Aug2025
              Type: published
              Y: 2025
          Identifiers:
            – Type: issn-print
              Value: 13807501
          Numbering:
            – Type: volume
              Value: 84
            – Type: issue
              Value: 27
          Titles:
            – TitleFull: Multimedia Tools & Applications
              Type: main
ResultId 1