Optimal asset allocation for outperforming a stochastic benchmark target

DOI10.1080/14697688.2022.2072233MaRDI QIDQ5039625zbMATH OpenOpenAlexWikidataFDO

Authors Chendi Ni, Yuying Li, Ray Carroll, P. A. Forsyth

Publication date 30 September 2022

Published in Quantitative Finance (Search for Journal in Brave)

Full work available at URL https://arxiv.org/abs/2006.15384

zbMATH Keywords

block bootstrap resamplingdefined contribution pension planneural network optimizationoptimal multi-period dynamic asset allocation strategystochastic benchmark target portfolio

Mathematics Subject Classification ID

Neural nets and related approaches to inference from stochastic processes (62M45) Applications of statistics to actuarial sciences and financial mathematics (62P05) Artificial neural networks and deep learning (68T07) Actuarial mathematics (91G05) Portfolio theory (91G10)

Abstract: We propose a data-driven Neural Network (NN) optimization framework to determine the optimal multi-period dynamic asset allocation strategy for outperforming a general stochastic target. We formulate the problem as an optimal stochastic control with an asymmetric, distribution shaping, objective function. The proposed framework is illustrated with the asset allocation problem in the accumulation phase of a defined contribution pension plan, with the goal of achieving a higher terminal wealth than a stochastic benchmark. We demonstrate that the data-driven approach is capable of learning an adaptive asset allocation strategy directly from historical market returns, without assuming any parametric model of the financial market dynamics. Following the optimal adaptive strategy, investors can make allocation decisions simply depending on the current state of the portfolio. The optimal adaptive strategy outperforms the benchmark constant proportion strategy, achieving a higher terminal wealth with a 90% probability, a 46% higher median terminal wealth, and a significantly more right-skewed terminal wealth distribution. We further demonstrate the robustness of the optimal adaptive strategy by testing the performance of the strategy on bootstrap resampled market data, which has different distributions compared to the training data.

Recommendations

• A data-driven neural network approach to optimal asset allocation for target based defined contribution pension plans
• Beating a Benchmark: Dynamic Programming May Not Be the Right Numerical Approach
• A benchmarking approach to optimal asset allocation for insurers and pension funds
• Outperformance and tracking: dynamic asset allocation for active and passive portfolio management
• Stochastic lifestyling: optimal dynamic asset allocation for defined contribution pension plans

Cites work

• A benchmarking approach to optimal asset allocation for insurers and pension funds
• A data-driven neural network approach to optimal asset allocation for target based defined contribution pension plans
• A jump-diffusion model for option pricing
• A neural network approach to efficient valuation of large portfolios of variable annuities
• A stochastic control approach to defined contribution plan decumulation: \textit{``The nastiest, hardest problem in finance}
• An Interior Trust Region Approach for Nonlinear Minimization Subject to Bounds
• Asset Allocation with Regime-Switching: Discrete-Time Case
• Automatic Block-Length Selection for the Dependent Bootstrap
• Beating a moving target: optimal portfolio strategies for outperforming a stochastic benchmark
• Better than pre-commitment mean-variance portfolio allocation strategies: a semi-self-financing Hamilton-Jacobi-Bellman equation approach
• Continuous time mean-variance optimal portfolio allocation under jump diffusion: an numerical impulse control approach
• Correction to “Automatic Block-Length Selection for the Dependent Bootstrap” by D. Politis and H. White
• scientific article; zbMATH DE number 1304947 (Why is no real title available?)
• Multi-stage stochastic linear programs for portfolio optimization
• Nonparametric tests for pathwise properties of semimartingales
• Numerical solution of the Hamilton-Jacobi-Bellman formulation for continuous time mean variance asset allocation
• On the distribution of terminal wealth under dynamic mean-variance optimal investment strategies
• Optimal Asset Allocation for Retirement Saving: Deterministic Vs. Time Consistent Adaptive Strategies
• Optimal investment decisions when time-horizon is uncertain
• Optimal investment with minimum performance constraints
• Optimal portfolio allocations with tracking error volatility and stochastic hedging constraints
• Optimum consumption and portfolio rules in a continuous-time model
• Outperformance and tracking: dynamic asset allocation for active and passive portfolio management
• Risk Management with Benchmarking
• Risk-constrained dynamic active portfolio management
• Risk-sensitive benchmarked asset management
• Stochastic network optimization models for investment planning
• Stochastic portfolio theory optimization and the origin of rule-based investing
• Survival and Growth with a Liability: Optimal Portfolio Strategies in Continuous Time
• The Stationary Bootstrap

Cited in

(23)

• Portfolio management in the binomial model: conditions for outperforming benchmarks
• A data-driven approach for a class of stochastic dynamic optimization problems
• A data-driven neural network approach to optimal asset allocation for target based defined contribution pension plans
• Optimal Asset Allocation for Passive Investing with Capital Loss Harvesting
• A nonlinear control policy using kernel method for dynamic asset allocation
• Revisiting the \(1/N\)-strategy: a neural network framework for optimal strategies
• Multi-Period Mean Expected-Shortfall Strategies: ‘Cut Your Losses and Ride Your Gains’
• BEATING A CONSTANT WEIGHT BENCHMARK: EASIER DONE THAN SAID
• Supervised portfolios
• Beating a Benchmark: Dynamic Programming May Not Be the Right Numerical Approach
• Optimal performance of a tontine overlay subject to withdrawal constraints
• Across-time risk-aware strategies for outperforming a benchmark
• A modified CTGAN-plus-features-based method for optimal asset allocation
• Deep learning for enhanced index tracking
• End-to-end risk budgeting portfolio optimization with neural networks
• Neural network approach to portfolio optimization with leverage constraints: a case study on high inflation investment
• An extended Merton problem with relaxed benchmark tracking
• Optimal multi-period leverage-constrained portfolios: a neural network approach
• A Global-in-Time Neural Network Approach to Dynamic Portfolio Optimization
• On optimal tracking portfolio in incomplete markets: the reinforcement learning approach
• Smart leverage? Rethinking the role of Leveraged Exchange Traded Funds in constructing portfolios to beat a benchmark
• Optimal consumption under relaxed benchmark tracking and consumption drawdown constraint
• Risk Measures for Defined Contribution (DC) Pension Plan Decumulation

This page was built for publication: Optimal asset allocation for outperforming a stochastic benchmark target

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q5039625)