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
  • [1] Generalized Groves of Neural Additive Models: Pursuing Transparent Machine Learning Models in Finance
    Chen, Dangxing
    Ye, Weicheng
    2024 IEEE SYMPOSIUM ON COMPUTATIONAL INTELLIGENCE FOR FINANCIAL ENGINEERING AND ECONOMICS, CIFER 2024, 2024,
  • [2] Review of Machine Learning models for Credit Scoring Analysis
    Kumar, Madapuri Rudra
    Gunjan, Vinit Kumar
    INGENIERIA SOLIDARIA, 2020, 16 (01):
  • [3] Transparency, auditability, and explainability of machine learning models in credit scoring
    Buecker, Michael
    Szepannek, Gero
    Gosiewska, Alicja
    Biecek, Przemyslaw
    JOURNAL OF THE OPERATIONAL RESEARCH SOCIETY, 2022, 73 (01) : 70 - 90
  • [4] Credit Risk Scoring Analysis Based on Machine Learning Models
    Qiu, Ziyue
    Li, Yuming
    Ni, Pin
    Li, Gangmin
    2019 6TH INTERNATIONAL CONFERENCE ON INFORMATION SCIENCE AND CONTROL ENGINEERING (ICISCE 2019), 2019, : 220 - 224
  • [5] Neural network credit scoring models
    West, D
    COMPUTERS & OPERATIONS RESEARCH, 2000, 27 (11-12) : 1131 - 1152
  • [6] Credit scoring using machine learning and deep Learning-Based models
    Mestiri, Sami
    DATA SCIENCE IN FINANCE AND ECONOMICS, 2024, 4 (02): : 236 - 248
  • [7] Neural Additive Models: Interpretable Machine Learning with Neural Nets
    Agarwal, Rishabh
    Melnick, Levi
    Frosst, Nicholas
    Zhang, Xuezhou
    Lengerich, Ben
    Caruana, Rich
    Hinton, Geoffrey E.
    ADVANCES IN NEURAL INFORMATION PROCESSING SYSTEMS 34 (NEURIPS 2021), 2021, 34
  • [8] Statistical and machine learning models in credit scoring: A systematic literature survey
    Dastile, Xolani
    Celik, Turgay
    Potsane, Moshe
    APPLIED SOFT COMPUTING, 2020, 91
  • [9] Sectorial Analysis Impact on the Development of Credit Scoring Machine Learning Models
    El-Qadi, Ayoub
    Trocan, Maria
    Frossard, Thomas
    Diaz-Rodriguez, Natalia
    PROCEEDINGS OF 2022 14TH INTERNATIONAL CONFERENCE ON MANAGEMENT OF DIGITAL ECOSYSTEMS, MEDES 2022, 2022, : 115 - 122
  • [10] Generalized Partially Linear Additive Models for Credit Scoring
    Shim, Ju-Hyun
    Lee, Young K.
    KOREAN JOURNAL OF APPLIED STATISTICS, 2011, 24 (04) : 587 - 595