# Are Logistic Models Really Interpretable?

arXiv: https://arxiv.org/abs/2406.13427 · HTML: https://mlsanity.com/paper/2406.13427/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 20 of its 70 references that are in the map.
- First posted on arXiv 19 Jun 2024.

## Builds on (most cited first, 20 of 20)

- [XGBoost: A Scalable Tree Boosting System](https://mlsanity.com/paper/1603.02754/) (2016)
- [Towards A Rigorous Science of Interpretable Machine Learning](https://mlsanity.com/paper/1702.08608/) (2017)
- [Fooling LIME and SHAP: Adversarial Attacks on Post hoc Explanation Methods](https://mlsanity.com/paper/1911.02508/) (2019)
- [Manipulating and Measuring Model Interpretability](https://mlsanity.com/paper/1802.07810/) (2018)
- [Explainable Machine Learning in Deployment](https://mlsanity.com/paper/1909.06342/) (2019)
- [Should we really use post-hoc tests based on mean-ranks?](https://mlsanity.com/paper/1505.02288/) (2015)
- [Do Feature Attribution Methods Correctly Attribute Features?](https://mlsanity.com/paper/2104.14403/) (2021)
- [Boolean Decision Rules via Column Generation](https://mlsanity.com/paper/1805.09901/) (2018)
- [How do Humans Understand Explanations from Machine Learning Systems? An Evaluation of the Human-Interpretability of Explanation](https://mlsanity.com/paper/1802.00682/) (2018)
- [Fairness and Accountability Design Needs for Algorithmic Support in High-Stakes Public Sector Decision-Making](https://mlsanity.com/paper/1802.01029/) (2018)
- [Born-Again Tree Ensembles](https://mlsanity.com/paper/2003.11132/) (2020)
- [Explainable Neural Networks based on Additive Index Models](https://mlsanity.com/paper/1806.01933/) (2018)
- [Enhancing Explainability of Neural Networks through Architecture Constraints](https://mlsanity.com/paper/1901.03838/) (2019)
- [Enforcing Interpretability and its Statistical Impacts: Trade-offs between Accuracy and Interpretability](https://mlsanity.com/paper/2010.13764/) (2020)
- [Designing Inherently Interpretable Machine Learning Models](https://mlsanity.com/paper/2111.01743/) (2021)
- [A Holistic Approach to Interpretability in Financial Lending: Models, Visualizations, and Summary-Explanations](https://mlsanity.com/paper/2106.02605/) (2021)
- [Forecasting remaining useful life: Interpretable deep learning approach via variational Bayesian inferences](https://mlsanity.com/paper/1907.05146/) (2019)
- [Sample size calculations for the experimental comparison of multiple algorithms on multiple problem instances](https://mlsanity.com/paper/1908.01720/) (2019)
- [Marginal Effects for Non-Linear Prediction Functions](https://mlsanity.com/paper/2201.08837/) (2022)
- [Regionally Additive Models: Explainable-by-design models minimizing feature interactions](https://mlsanity.com/paper/2309.12215/) (2023)

## Built on by (most cited first, 1 of 1)

- [Empirical Characterization of Rationale Stability Under Controlled Perturbations for Explainable Pattern Recognition](https://mlsanity.com/paper/2604.04456/) (2026)

## Abstract (arXiv)

The demand for open and trustworthy AI models points towards widespread publishing of model weights. Consumers of these model weights must be able to act accordingly with the information provided. That said, one of the simplest AI classification models, Logistic Regression (LR), has an unwieldy interpretation of its model weights, with greater difficulties when extending LR to generalised additive models. In this work, we show via a User Study that skilled participants are unable to reliably reproduce the action of small LR models given the trained parameters. As an antidote to this, we define Linearised Additive Models (LAMs), an optimal piecewise linear approximation that augments any trained additive model equipped with a sigmoid link function, requiring no retraining. We argue that LAMs are more interpretable than logistic models -- survey participants are shown to solve model reasoning tasks with LAMs much more accurately than with LR given the same information. Furthermore, we show that LAMs do not suffer from large performance penalties in terms of ROC-AUC and calibration with respect to their logistic counterparts on a broad suite of public financial modelling data.