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
  • [41] How to Measure the Quality of Credit Scoring Models
    Rezac, Martin
    Rezac, Frantisek
    FINANCE A UVER-CZECH JOURNAL OF ECONOMICS AND FINANCE, 2011, 61 (05): : 486 - 507
  • [42] A class of categorization methods for credit scoring models
    Silva, Diego M. B.
    Pereira, Gustavo H. A.
    Magalhaes, Tiago M.
    EUROPEAN JOURNAL OF OPERATIONAL RESEARCH, 2022, 296 (01) : 323 - 331
  • [43] Chaos in the Scoring Models from the Credit System
    Zhang, Naiyue
    Zhang, Xueyan
    Zhang, Li
    Chen, Zhong
    2008 IEEE INTERNATIONAL SYMPOSIUM ON KNOWLEDGE ACQUISITION AND MODELING WORKSHOP PROCEEDINGS, VOLS 1 AND 2, 2008, : 1 - +
  • [44] Credit Risk Scoring with Bayesian Network Models
    Chee Kian Leong
    Computational Economics, 2016, 47 : 423 - 446
  • [45] Building classification models for customer credit scoring
    Benyacoub, Badreddine
    El Bernoussi, Souad
    Zoglat, Abdelhak
    PROCEEDINGS OF 2014 2ND IEEE INTERNATIONAL CONFERENCE ON LOGISTICS AND OPERATIONS MANAGEMENT (GOL 2014), 2014, : 107 - 111
  • [46] Credit Risk Scoring with Bayesian Network Models
    Leong, Chee Kian
    COMPUTATIONAL ECONOMICS, 2016, 47 (03) : 423 - 446
  • [47] Customer Credit Risk: Application and Evaluation of Machine Learning and Deep Learning Models
    Yemmanuru, Prathibha Kiran
    Yeboah, Jones
    Nti, Isaac Kofi
    2024 IEEE 3RD INTERNATIONAL CONFERENCE ON COMPUTING AND MACHINE INTELLIGENCE, ICMI 2024, 2024,
  • [48] Credit scoring models for the microfinance industry using neural networks: Evidence from Peru
    Blanco, Antonio
    Pino-Mejias, Rafael
    Lara, Juan
    Rayo, Salvador
    EXPERT SYSTEMS WITH APPLICATIONS, 2013, 40 (01) : 356 - 364
  • [49] Geometrical defect detection for additive manufacturing with machine learning models
    Li, Rui
    Jin, Mingzhou
    Paquit, Vincent C.
    MATERIALS & DESIGN, 2021, 206
  • [50] ASYMPTOTIC PROPERTIES OF MONOTONIC LEARNING MODELS
    HOLMAN, EW
    JOURNAL OF MATHEMATICAL PSYCHOLOGY, 1969, 6 (03) : 456 - &