Understanding Machine Learning for Diversified Portfolio Construction by Explainable AI

Jaeger, Markus; Krügel, Stephan; Marinelli, Dimitri; Papenbrock, Jochen; Schwendner, Peter

doi:10.2139/ssrn.3528616

Cited by 2 publications

(1 citation statement)

References 1 publication

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The explanation [8] of a portfolio management strategy is important to investment banks, asset management companies and hedge funds. It helps traders understand the potential risk of a certain strategy.…”

Section: Introductionmentioning

confidence: 99%

Explainable Deep Reinforcement Learning for Portfolio Management: An Empirical Approach

Guan¹,

Liu²

2021

Preprint

View full text Add to dashboard Cite

Deep reinforcement learning (DRL) has been widely studied in the portfolio management task. However, it is challenging to understand a DRL-based trading strategy because of the black-box nature of deep neural networks. In this paper, we propose an empirical approach to explain the strategies of DRL agents for the portfolio management task. First, we use a linear model in hindsight as the reference model, which finds the best portfolio weights by assuming knowing actual stock returns in foresight. In particular, we use the coefficients of a linear model in hindsight as the reference feature weights. Secondly, for DRL agents, we use integrated gradients to define the feature weights, which are the coefficients between reward and features under a linear regression model. Thirdly, we study the prediction power in two cases, single-step prediction and multistep prediction. In particular, we quantify the prediction power by calculating the linear correlations between the feature weights of a DRL agent and the reference feature weights, and similarly for machine learning methods. Finally, we evaluate a portfolio management task on Dow Jones 30 constituent stocks during 01/01/2009 to 09/01/2021. Our approach empirically reveals that a DRL agent exhibits a stronger multi-step prediction power than machine learning methods.

show abstract

Section: Introductionmentioning

confidence: 99%

Explainable Deep Reinforcement Learning for Portfolio Management: An Empirical Approach

Guan¹,

Liu²

2021

Preprint

View full text Add to dashboard Cite

show abstract

Matrix Evolutions: Synthetic Correlations and Explainable Machine Learning for Constructing Robust Investment Portfolios

Papenbrock¹,

Schwendner²,

Jaeger³

et al. 2021

JFDS

Self Cite

View full text Add to dashboard Cite

The authors introduce the matrix evolutions concept based on an evolutionary algorithm to simulate correlation matrixes useful for financial market applications.n They apply the resulting synthetic correlation matrixes to benchmark hierarchical risk parity (HRP) and equal risk contribution allocations of a multi-asset futures portfolio and find HRP to show lower portfolio risk.n The authors evaluate three competing machine learning methods to regress the portfolio risk spread between both allocation methods against statistical features of the synthetic correlation matrixes and then discuss the local and global feature importance using the SHAP framework by Lundberg and Lee (2017).

show abstract

Understanding Machine Learning for Diversified Portfolio Construction by Explainable AI

Cited by 2 publications

References 1 publication

Explainable Deep Reinforcement Learning for Portfolio Management: An Empirical Approach

Explainable Deep Reinforcement Learning for Portfolio Management: An Empirical Approach

Matrix Evolutions: Synthetic Correlations and Explainable Machine Learning for Constructing Robust Investment Portfolios

Contact Info

Product

Resources

About