In this paper, we apply Solvency II indicators to find the optimal asset allocation of life insurance funds, for example by minimizing the Solvency Capital Requirement (SCR). SCR is defined as the level of available own fund that enables insurance companies to absorb significant losses of the available capital (AC) and that gives reasonable certainty to policyholders and beneficiaries that payments will be made as they fall due. The AC is the result, in the company balance sheet, of the difference between the fair value of assets and the fair value of all liabilities. The asset-liability interaction is evident in the literature concerning the valuation of life insurance policies. Then, the liability value depends on the chosen asset allocation and this makes the optimization procedure more complex and computational challenging. In literature and among practitioners, the most used numerical methods to reconstruct the AC distribution and to calculate the SCR are nested Monte Carlo, least square Monte Carlo and replicating portfolios. In this work, we propose a neural network approach to manage the optimization of the life insurance portfolio for a wide range of asset allocations. Furthermore, the robustness of the approach is tested and the performance is compared with existing numerical methods.

Asset allocation for life insurance portfolio under Solvency II using artificial intelligence

Anna Maria Gambaro
2022-01-01

Abstract

In this paper, we apply Solvency II indicators to find the optimal asset allocation of life insurance funds, for example by minimizing the Solvency Capital Requirement (SCR). SCR is defined as the level of available own fund that enables insurance companies to absorb significant losses of the available capital (AC) and that gives reasonable certainty to policyholders and beneficiaries that payments will be made as they fall due. The AC is the result, in the company balance sheet, of the difference between the fair value of assets and the fair value of all liabilities. The asset-liability interaction is evident in the literature concerning the valuation of life insurance policies. Then, the liability value depends on the chosen asset allocation and this makes the optimization procedure more complex and computational challenging. In literature and among practitioners, the most used numerical methods to reconstruct the AC distribution and to calculate the SCR are nested Monte Carlo, least square Monte Carlo and replicating portfolios. In this work, we propose a neural network approach to manage the optimization of the life insurance portfolio for a wide range of asset allocations. Furthermore, the robustness of the approach is tested and the performance is compared with existing numerical methods.
2022
978-951-95254-1-9
File in questo prodotto:
File Dimensione Formato  
program-euro32.pdf

file ad accesso aperto

Tipologia: Abstract
Licenza: Dominio pubblico
Dimensione 3.28 MB
Formato Adobe PDF
3.28 MB Adobe PDF Visualizza/Apri

I documenti in IRIS sono protetti da copyright e tutti i diritti sono riservati, salvo diversa indicazione.

Utilizza questo identificativo per citare o creare un link a questo documento: https://hdl.handle.net/11579/146259
Citazioni
  • ???jsp.display-item.citation.pmc??? ND
  • Scopus ND
  • ???jsp.display-item.citation.isi??? ND
social impact