Monotonic Neural Additive Models: Pursuing Regulated Machine Learning Models for Credit Scoring

被引:4
|
作者
Chen, Dangxing [1 ]
Ye, Weicheng [1 ]
机构
[1] Duke Kunshan Unnivers, Zu Chongzhi Ctr Math & Computat Sci, Kunshan, Jiangsu, Peoples R China
关键词
neural networks; model explainability; fairness; ART CLASSIFICATION ALGORITHMS;
D O I
10.1145/3533271.3561691
中图分类号
F8 [财政、金融];
学科分类号
0202 ;
摘要
The forecasting of credit default risk has been an active research field for several decades. Historically, logistic regression has been used as a major tool due to its compliance with regulatory requirements: transparency, explainability, and fairness. In recent years, researchers have increasingly used complex and advanced machine learning methods to improve prediction accuracy. Even though a machine learning method could potentially improve the model accuracy, it complicates simple logistic regression, deteriorates explainability, and often violates fairness. In the absence of compliance with regulatory requirements, even highly accurate machine learning methods are unlikely to be accepted by companies for credit scoring. In this paper, we introduce a novel class of monotonic neural additive models, which meet regulatory requirements by simplifying neural network architecture and enforcing monotonicity. By utilizing the special architectural features of the neural additive model, the monotonic neural additive model penalizes monotonicity violations effectively. Consequently, the computational cost of training a monotonic neural additive model is similar to that of training a neural additive model, as a free lunch. We demonstrate through empirical results that our new model is as accurate as black-box fully-connected neural networks, providing a highly accurate and regulated machine learning method.
引用
收藏
页码:70 / 78
页数:9
相关论文
共 50 条
  • [31] Sample selection in credit-scoring models
    Greene, W
    JAPAN AND THE WORLD ECONOMY, 1998, 10 (03) : 299 - 316
  • [32] CREDIT SCORING MODELS FOR MICROCREDITS: A LITERATURE REVIEW
    Seijas Gimenez, Maria Nela
    Fernandez-Lopez, Sara
    Vivel-Bua, Milagros
    ENTREPRENEURS. ENTREPRENEURSHIP: CHALLENGES AND OPPORTUNITIES IN THE 21ST CENTURY, 2017, : 63 - 73
  • [33] Sample selection bias in credit scoring models
    Banasik, J
    Crook, J
    Thomas, L
    JOURNAL OF THE OPERATIONAL RESEARCH SOCIETY, 2003, 54 (08) : 822 - 832
  • [34] Consumer credit scoring models with limited data
    Sustersic, Maia
    Mramor, Dusan
    Zupan, Jure
    EXPERT SYSTEMS WITH APPLICATIONS, 2009, 36 (03) : 4736 - 4744
  • [35] Application of credit scoring models in electricity companies
    Shen, Aihua
    Tong, Rencheng
    Li, Xingsen
    PROGRESS IN INTELLIGENCE COMPUTATION AND APPLICATIONS, PROCEEDINGS, 2007, : 618 - 621
  • [36] CREDIT-SCORING BY ENLARGED DISCRIMINANT MODELS
    FALBO, P
    OMEGA-INTERNATIONAL JOURNAL OF MANAGEMENT SCIENCE, 1991, 19 (04): : 275 - 289
  • [37] Geolocation Risk Scores for Credit Scoring Models
    Unal, Erdem
    Aydin, Ugur
    Koras, Murat
    Akgun, Baris
    Gonen, Mehmet
    MACHINE LEARNING, OPTIMIZATION, AND DATA SCIENCE, LOD 2023, PT II, 2024, 14506 : 34 - 44
  • [38] Credit Scoring Models Using Ensemble Learning and Classification Approaches: A Comprehensive Survey
    Tripathi, Diwakar
    Shukla, Alok Kumar
    Reddy, B. Ramachandra
    Bopche, Ghanshyam S.
    Chandramohan, D.
    WIRELESS PERSONAL COMMUNICATIONS, 2022, 123 (01) : 785 - 812
  • [39] SELECTION BIAS REDUCTION IN CREDIT SCORING MODELS
    Ditrich, Josef
    9TH INTERNATIONAL DAYS OF STATISTICS AND ECONOMICS, 2015, : 325 - 334
  • [40] Credit Scoring Models Using Ensemble Learning and Classification Approaches: A Comprehensive Survey
    Diwakar Tripathi
    Alok Kumar Shukla
    B. Ramachandra Reddy
    Ghanshyam S. Bopche
    D. Chandramohan
    Wireless Personal Communications, 2022, 123 : 785 - 812