A Data Driven Neural Network Approach to Optimal Asset Allocation for Target Based Defined Contribution Pension Plans

27 Pages Posted: 21 Jun 2018

See all articles by Yuying Li

Yuying Li

University of Waterloo

Peter Forsyth

University of Waterloo - David R. Cheriton School of Computer Science

Date Written: June 6, 2018

Abstract

A data driven Neural Network (NN) optimization framework is proposed to determine optimal asset allocation during the accumulation phase of a defined contribution pension scheme. In contrast to parametric model based solutions computed by a partial differential equation approach, the proposed computational framework can scale to high dimensional multi-asset problems. More importantly, the proposed approach can determine the optimal NN control directly from market returns, without assuming a particular parametric model for the return process. We validate the proposed NN learning solution by comparing the NN control to the optimal control determined by solution of the Hamilton-Jacobi-Bellman (HJB) equation. The HJB equation solution is based on a double exponential jump model calibrated to the historical market data. The NN control achieves nearly optimal performance. An alternative data driven approach (without the need of a parametric model) is based on using the historic bootstrap resampling data sets. Robustness is checked by training with a blocksize different from the test data. In both two and three asset cases, we compare performance of the NN controls directly learned from the market return sample paths and demonstrate that they always significantly outperform constant proportion strategies.

Keywords: DC plan asset allocation, data-driven, neural network, target based objective

JEL Classification: C61, D81, G11, G22

Suggested Citation

Li, Yuying and Forsyth, Peter, A Data Driven Neural Network Approach to Optimal Asset Allocation for Target Based Defined Contribution Pension Plans (June 6, 2018). Available at SSRN: https://ssrn.com/abstract=3192132 or http://dx.doi.org/10.2139/ssrn.3192132

Yuying Li

University of Waterloo ( email )

Waterloo, Ontario N2L 3G1
Canada

Peter Forsyth (Contact Author)

University of Waterloo - David R. Cheriton School of Computer Science ( email )

200 University Avenue West
Waterloo, ON
Canada

Register to save articles to
your library

Register

Paper statistics

Downloads
54
rank
368,357
Abstract Views
237
PlumX Metrics