This repo contains code for my PhD (2018-2022) research in machine & deep learning in the context of actuarial science. Code enables interested researches to train, test and run the respective models. Relevant papers include
1/ Kiermayer, M., Weiß, C. (2024). Neural calibration of hidden inhomogeneous Markov chains: informa-
tion decompression in life insurance. Mach Learn 113, 7129–7156 (2024). https://doi.org/10.1007/s10994-024-06551-w
2/ Kiermayer, M. (2022). Modeling Surrender Risk in Life Insurance: theoretical and experimental insight.
Scandinavian Actuarial Journal, 2022(7), 627–658. https://doi.org/10.1080/03461238.2021.2013308
3/ Kiermayer, M., Weiß, C. (2021). Grouping of contracts in insurance using neural networks. Scandinavian
Actuarial Journal 2021(4), 295–322. https://doi.org/10.1080/03461238.2020.1836676
More generally about me:
Languages in my toolbox
- python
- matlab
- R
Things that interest me include
- understanding new modelling approaches
- transfering ideas to new fields of application
- speeding up code and training of models
I'm curious to learn more about
- distributed training
- cloud computing
- learning theory
If you want to connect, I'll be happy to read your message on LinkedIn