no code implementations • 2 Sep 2022 • Mathias Lindholm, Ronald Richman, Andreas Tsanakas, Mario V. Wüthrich
This is particularly the case in insurance pricing where protected policyholder characteristics are not allowed to be used for insurance pricing.
no code implementations • 6 Jul 2022 • Mathias Lindholm, Ronald Richman, Andreas Tsanakas, Mario V. Wüthrich
Here, we address this issue by using a multi-task neural network architecture for claim predictions, which can be trained using only partial information on protected characteristics, and it produces prices that are free from proxy discrimination.
no code implementations • 8 Dec 2020 • Karim Barigou, Valeria Bignozzi, Andreas Tsanakas
Current approaches to fair valuation in insurance often follow a two-step approach, combining quadratic hedging with application of a risk measure on the residual liability, to obtain a cost-of-capital margin.