Multi periods mean-DCVaR optimization: a Recursive Neural Network resolution

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Lelong, Jérôme, Maume-Deschamps, Véronique, Thevenot, William
Format: Preprint
Published: 2026
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866908967965294592
author Lelong, Jérôme
Maume-Deschamps, Véronique
Thevenot, William
author_facet Lelong, Jérôme
Maume-Deschamps, Véronique
Thevenot, William
contents We study a discrete-time multi-period portfolio optimization problem under an explicit constraint on the Deviation Conditional Value-at-Risk (DCVaR), defined as the excess of Conditional Value-at-Risk over expected terminal wealth. The objective is to maximize expected return subject to a global tail-risk constraint, leading to a time-inconsistent precommitment problem. We propose a recurrent neural-network-based approach to approximate the optimal precommitment policy, which accommodates path-dependent risk constraints and highdimensional state dynamics without relying on dynamic programming. The explicit constraint formulation allows for exact penalty methods and provides a transparent notion of feasibility. The methodology is validated in a classical complete-market financial model and extended to a multi-period portfolio allocation problem in (re)insurance, capturing the long-term risk dynamics of insurance liabilities.
format Preprint
id arxiv_https___arxiv_org_abs_2604_14439
institution arXiv
publishDate 2026
record_format arxiv
spellingShingle Multi periods mean-DCVaR optimization: a Recursive Neural Network resolution
Lelong, Jérôme
Maume-Deschamps, Véronique
Thevenot, William
Portfolio Management
We study a discrete-time multi-period portfolio optimization problem under an explicit constraint on the Deviation Conditional Value-at-Risk (DCVaR), defined as the excess of Conditional Value-at-Risk over expected terminal wealth. The objective is to maximize expected return subject to a global tail-risk constraint, leading to a time-inconsistent precommitment problem. We propose a recurrent neural-network-based approach to approximate the optimal precommitment policy, which accommodates path-dependent risk constraints and highdimensional state dynamics without relying on dynamic programming. The explicit constraint formulation allows for exact penalty methods and provides a transparent notion of feasibility. The methodology is validated in a classical complete-market financial model and extended to a multi-period portfolio allocation problem in (re)insurance, capturing the long-term risk dynamics of insurance liabilities.
title Multi periods mean-DCVaR optimization: a Recursive Neural Network resolution
topic Portfolio Management
url https://arxiv.org/abs/2604.14439