2023/06/18 by M. Chen, Mohammad Mahdi A. Shirazi, Chen, Marc +5
Business, Management and Accounting · Economics, Econometrics and Finance · Social Sciences · #35Q93 #65N06 #68T07 #91G #93E20 #Computational Finance (q-fin.CP) #FOS: Economics and business #FOS: Mathematics #Financial Literacy, Pension, Retirement Analysis #Insurance, Mortality, Demography, Risk Management #Optimization and Control (math.OC) #Stochastic processes and financial applications
paper · pdf · doi:10.48550/arxiv.2306.10582
openalex publication_date 2023/06/18 · openalex created_date 2025/10/10 · openalex updated_date 2026/07/28
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 The objective function of the optimal control problem is based on expected wealth withdrawn (EW) and expected shortfall (ES) that directly targets left-tail risk.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.