The paper evaluates TabPFN, a tabular foundation model, for motor insurance pricing by comparing it to generalized linear models (GLMs) and XGBoost on two motor third‑party liability datasets. Results show that TabPFN does not consistently outperform GLMs: it lags on claim frequency, especially when the in‑context training set is small, but performs competitively on claim severity where data are limited. Additionally, TabPFN’s inference times are substantially longer than those of the baseline methods.
arXiv:2605.18147v3 Announce Type: replace Abstract: Predictive models are central to credit risk management, where the accuracy of default-probability and loss estimates affects the profitability of...
The paper studies whether scaling laws similar to those in deep learning apply to actuarial ratemaking with tabular data. Using a motor insurance portfolio, it trains various model families on increasing data fractions and evaluates out‑of‑sample Poisson deviance. Results show all models improve with more data, but TabM outperforms Transformers and MLPs in data scaling, while Transformers need inductive biases to scale effectively.
arXiv:2605. 18147v2 Announce Type: replace Abstract: Predictive models play a pivotal role in credit risk management, guiding critical decisions through accurate estimation of default probabilities and losses.
Mitra‑v2 is a tabular foundation model that achieves state‑of‑the‑art performance on a wide range of real‑world classification and regression tasks, including credit‑risk scoring, clinical prediction, equipment‑failure detection, and house‑price estimation. Trained solely on synthetic data with a larger and more diverse pretraining distribution than its predecessor, it uses a compact 2D Transformer backbone and improved optimization to handle longer contexts and larger feature spaces. On the TabArena and TALENT benchmarks, Mitra‑v2 outperforms leading models such as TabPFN‑3 and TabICLv2, matching the performance of a 1.6B‑parameter TabFM with only 77M parameters, and ranks first on multi‑class classification tasks with more than ten classes.
The paper proposes a framework for making machine‑learning based insurance premiums explainable in a way that is valid, actionable, and reliable. It introduces axioms for each property and develops a method that uses Conformal Prediction to filter out uncertain recommendations, ensuring that suggested changes to controllable characteristics are likely to lower premiums. Experiments on real Florida flood‑insurance claims and synthetic driver‑telematics data show that constrained recommendations are more reliable and predict larger risk reductions than unconstrained ones.
arXiv:2608. 06137v1 Announce Type: new Abstract: Tabular data are ubiquitous in real-world applications and are crucial for data-driven prediction and decision-making across science, industry, finance, healthcare, and public services.
The paper introduces a model‑based boosting method for fitting structured additive distributional copula regression models with bivariate responses, specifically targeting joint modeling of insurance claim frequency and severity. It builds on generalized additive models for location, scale, and shape (GAMLSS), allowing multiple distribution parameters to depend on covariates and thus providing interpretable additive predictors. The authors evaluate the framework on synthetic and real data, showing it can recover covariate effects, capture dependence structure, identify informative variables, and match benchmark predictive performance while offering transparent interpretation.
arXiv:2609.37959v1 Announce Type: new Abstract: Tabular machine learning typically relies on per-dataset workflows, fitting tree ensembles or running AutoML searches from scratch for every task. We p...
arXiv:2601. 22259v2 Announce Type: replace Abstract: While tabular foundation models have achieved remarkable success in classification and regression, adapting them to model time-to-event outcomes for survival analysis is non-trivial due to right-censoring, where data observations may end before the event of interest occurs.
arXiv:2606. 12006v1 Announce Type: cross Abstract: Predicting time-to-event outcomes such as mortality is a fundamental task in clinical decision-making, commonly addressed through survival analysis.
arXiv:2606. 15314v1 Announce Type: cross Abstract: Industrial retrofit planning depends on structured operational data rather than free text: planners must estimate whether a newly registered prototype will require a retrofit, which retrofit package it will need, and how long the work will take.
arXiv:2601. 20819v2 Announce Type: replace-cross Abstract: Machine learning predictions are increasingly used to supplement incomplete or costly-to-measure outcomes in fields such as biomedical research, environmental science, and social science.