Portfolio Optimization with Feedback Strategies Based on Artificial Neural Networks

TL;DR

This paper explores a novel ANN-based empirical utility maximization approach for dynamic portfolio optimization, demonstrating its effectiveness in various market models and offering a transparent, market-agnostic alternative to traditional HJB methods.

Contribution

It introduces an ANN-driven empirical utility maximization method for portfolio optimization that bypasses complex HJB solutions and is applicable across different market dynamics.

Findings

ANN approach achieves results comparable to theoretical optimal weights.

Method is simple, transparent, and market-agnostic.

Validated on models including geometric Brownian motion and Heston.

Abstract

With the recent advancements in machine learning (ML), artificial neural networks (ANN) are starting to play an increasingly important role in quantitative finance. Dynamic portfolio optimization is among many problems that have significantly benefited from a wider adoption of deep learning (DL). While most existing research has primarily focused on how DL can alleviate the curse of dimensionality when solving the Hamilton-Jacobi-Bellman (HJB) equation, some very recent developments propose to forego derivation and solution of HJB in favor of empirical utility maximization over dynamic allocation strategies expressed through ANN. In addition to being simple and transparent, this approach is universally applicable, as it is essentially agnostic about market dynamics. To showcase the method, we apply it to optimal portfolio allocation between a cash account and the S&P 500 index modeled using geometric Brownian motion or the Heston model. In both cases, the results are demonstrated to be on par with those under the theoretical optimal weights assuming isoelastic utility and real-time rebalancing. A set of R codes for a broad class of stochastic volatility models are provided as a supplement.