mlsanityData to 7 Oct 2026

How to address monotonicity for model risk management?

arXiv 2305.00799 ↗First posted 28 Apr 2023cs.LG q-fin.CPcited by 4

Not on the map. Why?

Abstract (arXiv)

In this paper, we study the problem of establishing the accountability and fairness of transparent machine learning models through monotonicity. Although there have been numerous studies on individual monotonicity, pairwise monotonicity is often overlooked in the existing literature. This paper studies transparent neural networks in the presence of three types of monotonicity: individual monotonicity, weak pairwise monotonicity, and strong pairwise monotonicity. As a means of achieving monotonicity while maintaining transparency, we propose the monotonic groves of neural additive models. As a result of empirical examples, we demonstrate that monotonicity is often violated in practice and that monotonic groves of neural additive models are transparent, accountable, and fair.

Key facts. Cited by 4 papers in the map (data through 7 Oct 2026). Builds on 15 of its 56 references that are in the map. First posted on arXiv 28 Apr 2023.

Builds on

15 of 56 references.

References · 15

  1. 2015Deep Residual Learning for Image Recognitioncited by 51,809
  2. 2016XGBoost: A Scalable Tree Boosting Systemcited by 5,120
  3. 2016Equality of Opportunity in Supervised Learningcited by 2,000
  4. 2017Preventing Fairness Gerrymandering: Auditing and Learning for Subgroup Fairnesscited by 381
  5. 2020Neural Additive Models: Interpretable Machine Learning with Neural Netscited by 318
  6. 2018An Intersectional Definition of Fairnesscited by 126
  7. 2020Explaining Explanations: Axiomatic Feature Interactions for Deep Networkscited by 103
  8. 2020GAMI-Net: An Explainable Neural Network based on Generalized Additive Models with Structured Interactionscited by 82
  9. 2018An Empirical Study of Rich Subgroup Fairness for Machine Learningcited by 81
  10. 2017Detecting Statistical Interactions from Neural Network Weightscited by 80
  11. 2020How does this interaction affect me? Interpretable attribution for feature interactionscited by 73
  12. 2017Deep Lattice Networks and Partial Monotonic Functionscited by 62
3 more
  1. 2017Distill-and-Compare: Auditing Black-Box Models Using Transparent Model Distillationcited by 62
  2. 2020Certified Monotonic Neural Networkscited by 51
  3. 2022Monotonic Neural Additive Models: Pursuing Regulated Machine Learning Models for Credit Scoringcited by 12

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2024: 2; 2025: 1; 2026: 1.

4 papers.

  1. 2026RiskProp: Collision-Anchored Self-Supervised Risk Propagation for Early Accident Anticipationcited by 2
  2. 2024Attribution Methods in Asset Pricing: Do They Account for Risk?cited by 1
  3. 2024FinML-Chain: A Blockchain-Integrated Dataset for Enhanced Financial Machine Learningcited by 1
  4. 2025Explaining Risks: Axiomatic Risk Attributions for Financial Modelscited by 0