Asset Allocation: From Markowitz to Deep Reinforcement Learning
Benchmarking asset allocation strategies from Markowitz to deep reinforcement learning under different market conditions.
What it examines
This paper explores asset allocation strategies, comparing traditional methods based on Modern Portfolio Theory with machine-learning approaches, particularly deep reinforcement learning, to optimize portfolio performance under varying market conditions.
What it concludes
The research suggests hybrid models combining traditional and DRL approaches for better stability and returns. Future work should explore incorporating more technical indicators and ethical considerations into DRL models for asset allocation.
Evidence objects
The research suggests hybrid models combining traditional and DRL approaches for better stability and returns. Future work should explore incorporating more technical indicators and ethical considerations into DRL models for asset allocation.
key_findings bullet 1 · key_findings · validation V0
Raw abstract and provenance
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… ▽ More 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. △ Less
Source row: 245 · abstract type: unknown