AI research uses RL to create a financial model-free solution for asset allocation

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.

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. Researchers Miquel Noguer i Alonso, from the Artificial Intelligence in Finance Institute, and Sonam Srivastava, from Wright Research demonstrate this on daily data for the top 24 stocks in the US equities universe with daily rebalancing. They use a deep reinforcement model on US stocks using different deep learning architectures. They 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. The researchers said that the modeling framework can deal with time series prediction and asset allocation, including transaction costs.

Read the full research paper

Related Posts

Previous Post
ISDA Launches IBOR Fallbacks Supplement and Protocol and animated video
Next Post
SFTR’s inclusion of buy-side data brings new trends and questions (Premium)

Related Posts

Fill out this field
Fill out this field
Please enter a valid email address.


Reset password

Create an account