Enhancing credit scoring accuracy with a comprehensive evaluation of alternative data

被引:3
|
作者
Hlongwane, Rivalani [1 ]
Ramaboa, Kutlwano K. K. M. [1 ]
Mongwe, Wilson [2 ]
机构
[1] Univ Cape, Grad Sch Business, Cape Town, South Africa
[2] Univ Johannesburg, Elect & Elect Engn, Johannesburg, South Africa
来源
PLOS ONE | 2024年 / 19卷 / 05期
关键词
ALGORITHMS; DEFAULT; MODEL; OPTIMIZATION; PERFORMANCE; PREDICTION; XGBOOST; AREA;
D O I
10.1371/journal.pone.0303566
中图分类号
O [数理科学和化学]; P [天文学、地球科学]; Q [生物科学]; N [自然科学总论];
学科分类号
07 ; 0710 ; 09 ;
摘要
This study explores the potential of utilizing alternative data sources to enhance the accuracy of credit scoring models, compared to relying solely on traditional data sources, such as credit bureau data. A comprehensive dataset from the Home Credit Group's home loan portfolio is analysed. The research examines the impact of incorporating alternative predictors that are typically overlooked, such as an applicant's social network default status, regional economic ratings, and local population characteristics. The modelling approach applies the model-X knockoffs framework for systematic variable selection. By including these alternative data sources, the credit scoring models demonstrate improved predictive performance, achieving an area under the curve metric of 0.79360 on the Kaggle Home Credit default risk competition dataset, outperforming models that relied solely on traditional data sources, such as credit bureau data. The findings highlight the significance of leveraging diverse, non-traditional data sources to augment credit risk assessment capabilities and overall model accuracy.
引用
收藏
页数:18
相关论文
共 50 条
  • [21] Enhancing U-Net Segmentation Accuracy Through Comprehensive Data Preprocessing
    Sarsembayeva, Talshyn
    Mansurova, Madina
    Abdildayeva, Assel
    Serebryakov, Stepan
    JOURNAL OF IMAGING, 2025, 11 (02)
  • [22] High Accuracy-priority Rule Extraction for Reconciling Accuracy and Interpretability in Credit Scoring
    Yoichi Hayashi
    Tatsuhiro Oishi
    New Generation Computing, 2018, 36 : 393 - 418
  • [23] High Accuracy-priority Rule Extraction for Reconciling Accuracy and Interpretability in Credit Scoring
    Hayashi, Yoichi
    Oishi, Tatsuhiro
    NEW GENERATION COMPUTING, 2018, 36 (04) : 393 - 418
  • [24] A novel framework for enhancing transparency in credit scoring: Leveraging Shapley values for interpretable credit scorecards
    Hlongwane, Rivalani
    Ramabao, Kutlwano
    Mongwe, Wilson
    PLOS ONE, 2024, 19 (08):
  • [25] CREDIT SCORING AS AN ALTERNATIVE TO MINIMIZE CREDIT RISK IN MICROFINANCE INSTITUTIONS DURING COVID-19
    Quiroz Calderon, Milagro Baldemar
    Torres Guzman, Roxana Milagros
    Montano Barbuda, Julio Javier
    Torres Garcia, Luis Alberto
    Rubio Cabrera, Wilberto Fernando
    REVISTA UNIVERSIDAD Y SOCIEDAD, 2022, 14 : 376 - 385
  • [26] Credit risk evaluation: a comprehensive study
    Arijit Bhattacharya
    Saroj Kr. Biswas
    Ardhendu Mandal
    Multimedia Tools and Applications, 2023, 82 : 18217 - 18267
  • [27] Credit risk evaluation: a comprehensive study
    Bhattacharya, Arijit
    Biswas, Saroj Kr
    Mandal, Ardhendu
    MULTIMEDIA TOOLS AND APPLICATIONS, 2023, 82 (12) : 18217 - 18267
  • [28] AN EVALUATION OF MMPI SCORING ACCURACY BY 2 NATIONAL SCORING AGENCIES
    WEIGEL, RG
    PHILLIPS, M
    JOURNAL OF CLINICAL PSYCHOLOGY, 1967, 23 (01) : 102 - &
  • [29] FOCUSING ON THE LOWER SCORING DATA IN ORDER TO IMPROVE CREDIT SCORING MODEL SELECTION
    Dryver, Arthur L.
    ADVANCES AND APPLICATIONS IN STATISTICS, 2011, 20 (01) : 25 - 41
  • [30] Credit scoring model: a comparative study based on Chinese real credit data
    Ren Jinzheng
    Chen Baofeng
    INTERNATIONAL CONFERENCE ON MANAGEMENT INNOVATION, VOLS 1 AND 2, 2007, : 425 - 429