Machine Learning and Hamilton-Jacobi-Bellman Equation for Optimal Decumulation: a Comparison Study
Preprint
Abstract
We propose a novel data-driven neural network (NN) optimization framework for solving an optimal stochastic control problem under stochastic constraints. Customized activation functions for the output layers of the NN are applied, which permits training via standard unconstrained optimization. The optimal solution yields a multi-period asset allocation and decumulation strategy for a holder of a defined contribution (DC) pension plan. The objective function of the optimal control problem is based on expected wealth withdrawn (EW) and expected shortfall (ES) that directly targets left-tail risk. The stochastic bound constraints enforce a guaranteed minimum withdrawal each year. We demonstrate that the data-driven approach is capable of learning a near-optimal solution by benchmarking it against the numerical results from a Hamilton-Jacobi-Bellman (HJB) Partial Differential Equation (PDE) computational framework.Keywords
All Related Versions
This publication has 32 references indexed in Scilit:
- Optimal performance of a tontine overlay subject to withdrawal constraintsASTIN Bulletin, 2023
- A three layer neural network can represent any multivariate functionJournal of Mathematical Analysis and Applications, 2023
- Stocks for the long run? Evidence from a broad sample of developed marketsJournal of Financial Economics, 2022
- Time-Inconsistent Control Theory with Finance Applications2021
- Better than pre-commitment mean-variance portfolio allocation strategies: A semi-self-financing Hamilton–Jacobi–Bellman equation approachEuropean Journal of Operational Research, 2016
- Testing rebalancing strategies for stock-bond portfolios across different asset allocationsApplied Economics, 2015
- De-risking defined benefit plansInsurance: Mathematics and Economics, 2015
- A theory of Markovian time-inconsistent stochastic control in discrete timeFinance and Stochastics, 2014
- Continuous time mean‐variance optimal portfolio allocation under jump diffusion: An numerical impulse control approachNumerical Methods for Partial Differential Equations, 2013
- Survey of multi-objective optimization methods for engineeringStructural and Multidisciplinary Optimization, 2004