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

TL;DR

This paper introduces monotonic neural additive models that ensure regulatory compliance in credit scoring by maintaining transparency and fairness while achieving accuracy comparable to black-box neural networks.

Contribution

The paper proposes a novel neural additive model enforcing monotonicity, balancing regulatory requirements with high prediction accuracy in credit risk modeling.

Findings

Model achieves accuracy comparable to fully-connected neural networks.

Enforces monotonicity to meet regulatory transparency and fairness.

Training cost is similar to that of standard neural additive models.

Abstract

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.