# A Spatio-Temporal Machine Learning Model for Mortgage Credit Risk: Default Probabilities and Loan Portfolios

arXiv: https://arxiv.org/abs/2410.02846 · HTML: https://mlsanity.com/paper/2410.02846/

## Key facts

- Cited by 2 papers in the map (data through 14 Oct 2026).
- Builds on 15 of its 74 references that are in the map.
- First posted on arXiv 3 Oct 2024.

## Builds on (most cited first, 15 of 15)

- [A Unified Approach to Interpreting Model Predictions](https://mlsanity.com/paper/1705.07874/) (2017)
- [Tabular Data: Deep Learning is Not All You Need](https://mlsanity.com/paper/2106.03253/) (2021)
- [Why do tree-based models still outperform deep learning on tabular data?](https://mlsanity.com/paper/2207.08815/) (2022)
- [Hierarchical Nearest-Neighbor Gaussian Process Models for Large Geostatistical Datasets](https://mlsanity.com/paper/1406.7343/) (2014)
- [A general framework for Vecchia approximations of Gaussian processes](https://mlsanity.com/paper/1708.06302/) (2017)
- [Gaussian Process Boosting](https://mlsanity.com/paper/2004.02653/) (2020)
- [Permutation and Grouping Methods for Sharpening Gaussian Process Approximations](https://mlsanity.com/paper/1609.05372/) (2016)
- [Gradient and Newton Boosting for Classification and Regression](https://mlsanity.com/paper/1808.03064/) (2018)
- [Correlation-based sparse inverse Cholesky factorization for fast Gaussian-process inference](https://mlsanity.com/paper/2112.14591/) (2021)
- [Gaussian Process Learning via Fisher Scoring of Vecchia's Approximation](https://mlsanity.com/paper/1905.08374/) (2019)
- [Latent Gaussian Model Boosting](https://mlsanity.com/paper/2105.08966/) (2021)
- [Evaluating Probabilistic Classifiers: The Triptych](https://mlsanity.com/paper/2301.10803/) (2023)
- [Grabit: Gradient Tree-Boosted Tobit Models for Default Prediction](https://mlsanity.com/paper/1711.08695/) (2017)
- [Iterative Methods for Vecchia-Laplace Approximations for Latent Gaussian Process Models](https://mlsanity.com/paper/2310.12000/) (2023)
- [Joint model for longitudinal and spatio-temporal survival data](https://mlsanity.com/paper/2311.04008/) (2023)

## Built on by (most cited first, 2 of 2)

- [Calibrated Credit Intelligence: Shift-Robust and Fair Risk Scoring with Bayesian Uncertainty and Gradient Boosting](https://mlsanity.com/paper/2603.06733/) (2026)
- [A Censored Transformed Model for Proportional Outcomes with Boundary Mass and an Application to Loss Given Default Modeling](https://mlsanity.com/paper/2606.21515/) (2026)

## Abstract (arXiv)

We introduce a novel machine learning model for credit risk by combining tree-boosting with a latent spatio-temporal Gaussian process model accounting for frailty correlation. This allows for modeling non-linearities and interactions among predictor variables in a flexible data-driven manner and for accounting for spatio-temporal variation that is not explained by observable predictor variables. We also show how estimation and prediction can be done in a computationally efficient manner. In an application to a large U.S. mortgage credit risk data set, we find that both predictive default probabilities for individual loans and predictive loan portfolio loss distributions obtained with our novel approach are more accurate compared to conventional independent linear hazard models and also linear spatio-temporal models. Using interpretability tools for machine learning models, we find that the likely reasons for this outperformance are strong interaction and non-linear effects in the predictor variables and the presence of spatio-temporal frailty effects.