# A new strategy for finite-sample valid prediction of future insurance claims in the regression setting

arXiv: https://arxiv.org/abs/2601.21153 · HTML: https://mlsanity.com/paper/2601.21153/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 5 of its 32 references that are in the map.
- First posted on arXiv 29 Jan 2026.

## Builds on (most cited first, 5 of 5)

- [Distribution-Free Predictive Inference For Regression](https://mlsanity.com/paper/1604.04173/) (2016)
- [Methods to Compute Prediction Intervals: A Review and New Results](https://mlsanity.com/paper/2011.03065/) (2020)
- [On overfitting and post-selection uncertainty assessments](https://mlsanity.com/paper/1712.02379/) (2017)
- [Conformal prediction of future insurance claims in the regression problem](https://mlsanity.com/paper/2503.03659/) (2025)
- [On some practical challenges of conformal prediction](https://mlsanity.com/paper/2510.10324/) (2025)

## Abstract (arXiv)

The extant insurance literature demonstrates a paucity of finite-sample valid prediction intervals of future insurance claims in the regression setting. To address this challenge, this article proposes a new strategy that converts a predictive method in the unsupervised iid (independent identically distributed) setting to a predictive method in the regression setting. In particular, it enables an actuary to obtain infinitely many finite-sample valid prediction intervals in the regression setting.