An Investigation of Machine Learning Approaches in the Solvency II Valuation Framework

25 Pages Posted: 3 Jan 2019

See all articles by Gilberto Castellani

Gilberto Castellani

University of Rome I

Ugo Fiore

University of Naples Parthenope - Department of Management Studies and Quantitative Methods

Zelda Marino

University of Naples Parthenope - Department of Management Studies and Quantitative Methods

Luca Passalacqua

La Sapienza, University of Rome

Francesca Perla

University of Naples Parthenope - Department of Management Studies and Quantitative Methods

Salvatore Scognamiglio

University of naples "Parthenope" Department of Economic and Legal Studies

Paolo Zanetti

University of Naples Parthenope - Department of Management Studies and Quantitative Methods

Date Written: December 14, 2018

Abstract

The insurance regulatory regime introduced in the European Union by the "Solvency II" Directive 2009/138, that has become applicable on January 1, 2016, is aimed to safeguard policyholders and beneficiaries by requiring insurance undertakings to hold own funds able to cover losses, in excess to the expected ones, at the 99.5% confidence level, over a one-year period. In order to assess risks and evaluate the regulatory Solvency Capital Requirement undertakings should compute the probability distribution of the Net Asset Value - i.e., value of assets minus value of liabilities - over a one-year period, with a financially inspired market consistent approach. In life insurance, given the peculiarities of the contracts, the valuation of the Net Asset Value distribution requires a nested Monte Carlo simulation, which is extremely time consuming.

Machine learning techniques are considered a promising candidate to reduce the computational burden of nested simulations. This work investigates the potential of well-established methods, such as Deep Learning Networks and Support Vector Regressors, when applied to the valuation of the Solvency Capital Requirement of participating life insurance polices, by empirically assessing their effectiveness and by comparing their efficiency and accuracy, also w.r.t. the "traditional" Least Squares Monte Carlo technique.

The work aims also to contribute to the global process of renewal of the European insurance industry, where Solvency II has made the board of directors fully responsible for the choice of evaluation techniques and algorithmic processes, under the periodic monitoring of national supervisory authorities.

Keywords: Solvency II, Nested Monte Carlo, With-Profit Insurance Policies, Least Squares Monte Carlo, Support Vector Machines, Deep Learning

Suggested Citation

Castellani, Gilberto and Fiore, Ugo and Marino, Zelda and Passalacqua, Luca and Perla, Francesca and Scognamiglio, Salvatore and Zanetti, Paolo, An Investigation of Machine Learning Approaches in the Solvency II Valuation Framework (December 14, 2018). Available at SSRN: https://ssrn.com/abstract=3303296 or http://dx.doi.org/10.2139/ssrn.3303296

Gilberto Castellani

University of Rome I ( email )

Piazzale Aldo Moro 5
Roma, Rome 00185
Italy

Ugo Fiore (Contact Author)

University of Naples Parthenope - Department of Management Studies and Quantitative Methods ( email )

Via Generale Parisi, 13
Via Medina 40
Naples, 80132
Italy

Zelda Marino

University of Naples Parthenope - Department of Management Studies and Quantitative Methods ( email )

Via Medina 40
Via Generale Parisi, 13
Naples, 80133
United States

Luca Passalacqua

La Sapienza, University of Rome ( email )

Viale Regina Elena, 295
Rome, 00161
Italy

Francesca Perla

University of Naples Parthenope - Department of Management Studies and Quantitative Methods ( email )

Via Medina 40
Via Generale Parisi, 13
Naples, 80133
United States

Salvatore Scognamiglio

University of naples "Parthenope" Department of Economic and Legal Studies ( email )

Italy

Paolo Zanetti

University of Naples Parthenope - Department of Management Studies and Quantitative Methods ( email )

Via Medina 40
Via Generale Parisi, 13
Naples, 80133
United States

Register to save articles to
your library

Register

Paper statistics

Downloads
240
Abstract Views
830
rank
127,483
PlumX Metrics