Deep Reinforcement Learning for Asset Allocation in US Equities

29 Pages Posted: 19 Oct 2020

See all articles by Miquel Noguer i Alonso

Miquel Noguer i Alonso

Artificial Intelligence in Finance Institute

Sonam Srivastava

Wright Research

Date Written: October 14, 2020


Reinforcement learning is a machine learning approach concerned with solving dynamic optimization problems in an almost model-free way by maximizing a reward function in state and action spaces. This property makes it an exciting area of research for financial problems. Asset allocation, where the goal is to obtain the weights of the assets that maximize the rewards in a given state of the market considering risk and transaction costs, is a problem easily framed using a reinforcement learning framework. So it is first a prediction problem for the vector of expected returns and covariance matrix and then an optimization problem for returns, risk, and market impact, usually a quadratic programming one. Investors and financial researchers have been working with approaches like mean-variance optimization, minimum variance, risk parity, and equally weighted and several methods to make expected returns and covariance matrices' predictions more robust and after use mean-variance like the Black Litterman model.

This paper demonstrates the application of reinforcement learning to create a financial model-free solution to the asset allocation problem, learning to solve the problem using time series and deep neural networks. We demonstrate this on daily data for the top 24 stocks in the US equities universe with daily rebalancing. We use a deep reinforcement model on US stocks using different deep learning architectures. We use Long Short Term Memory networks, Convolutional Neural Networks, and Recurrent Neural Networks and compare them with more traditional portfolio management approaches like mean-variance, minimum variance, risk parity, and equally weighted. The Deep Reinforcement Learning approach shows better results than traditional approaches using a simple reward function and only being given the time series of stocks. In Finance, no training to test error generalization results come guaranteed. We can say that the modeling framework can deal with time series prediction and asset allocation, including transaction costs.

Keywords: Artificial Intelligence, Reinforcement Learning, Portfolio Management, Deep Learning, Neural Networks

JEL Classification: C00, C10, C45, C50, G00, G11

Suggested Citation

Noguer i Alonso, Miquel and Srivastava, Sonam, Deep Reinforcement Learning for Asset Allocation in US Equities (October 14, 2020). Available at SSRN: or

Miquel Noguer i Alonso

Artificial Intelligence in Finance Institute ( email )

New York
United States

Sonam Srivastava (Contact Author)

Wright Research ( email )

Mumbai, 400098

Do you have a job opening that you would like to promote on SSRN?

Paper statistics

Abstract Views
PlumX Metrics