Neural Calibration of Hidden Inhomogeneous Markov Chains: Information Decompression in Life Insurance

Abstract

Markov chains play a key role in a vast number of areas, including life insurance mathematics. Standard actuarial quantities as the premium value can be interpreted as compressed, lossy information about the underlying Markov process. We introduce a method to reconstruct the underlying Markov chain given collective information of a portfolio of contracts. Our neural architecture characterizes the process in a highly explainable way by explicitly providing one-step transition probabilities. Further, we provide an intrinsic, economic model validation to inspect the quality of the information decompression. Lastly, our methodology is successfully tested for a realistic data set of German term life insurance contracts.

Cite

Text

Kiermayer and Weiß. "Neural Calibration of Hidden Inhomogeneous Markov Chains: Information Decompression in Life Insurance." Machine Learning, 2024. doi:10.1007/S10994-024-06551-W

Markdown

[Kiermayer and Weiß. "Neural Calibration of Hidden Inhomogeneous Markov Chains: Information Decompression in Life Insurance." Machine Learning, 2024.](https://mlanthology.org/mlj/2024/kiermayer2024mlj-neural/) doi:10.1007/S10994-024-06551-W

BibTeX

@article{kiermayer2024mlj-neural,
  title     = {{Neural Calibration of Hidden Inhomogeneous Markov Chains: Information Decompression in Life Insurance}},
  author    = {Kiermayer, Mark and Weiß, Christian},
  journal   = {Machine Learning},
  year      = {2024},
  pages     = {7129-7156},
  doi       = {10.1007/S10994-024-06551-W},
  volume    = {113},
  url       = {https://mlanthology.org/mlj/2024/kiermayer2024mlj-neural/}
}