Asset Allocation: From Markowitz to Deep Reinforcement Learning

TL;DR

This paper compares traditional Modern Portfolio Theory and deep reinforcement learning methods for asset allocation, evaluating their effectiveness across different market conditions through extensive benchmarking.

Contribution

It provides a comprehensive benchmark study assessing the performance and reliability of classical and machine learning-based asset allocation strategies.

Findings

Deep reinforcement learning shows promising results in dynamic market conditions.

Traditional methods remain robust in stable markets.

The study offers reproducible code for further research.

Abstract

Asset allocation is an investment strategy that aims to balance risk and reward by constantly redistributing the portfolio's assets according to certain goals, risk tolerance, and investment horizon. Unfortunately, there is no simple formula that can find the right allocation for every individual. As a result, investors may use different asset allocations' strategy to try to fulfil their financial objectives. In this work, we conduct an extensive benchmark study to determine the efficacy and reliability of a number of optimization techniques. In particular, we focus on traditional approaches based on Modern Portfolio Theory, and on machine-learning approaches based on deep reinforcement learning. We assess the model's performance under different market tendency, i.e., both bullish and bearish markets. For reproducibility, we provide the code implementation code in this repository.