Dynamic Portfolio Management with Machine Learning

81 Pages Posted: 17 Mar 2021

See all articles by Xinyu Huang

Xinyu Huang

University of Bath - School of Management

Massimo Guidolin

Bocconi University - Department of Finance

Emmanouil Platanakis

University of Bath - School of Management

David Newton

University of Bath - School of Management

Date Written: January 30, 2021

Abstract

We present a structured portfolio optimization framework with sparse inverse covariance estimation and an attention-based LSTM network that exploits machine learning (deep learning) techniques. We shrink Wishart volatility towards a Graphical Lasso initial covariance estimator and solve the portfolio optimization using a fast coordinate descent algorithm with regularization determined using a genetic algorithm. We further introduce a novel portfolio shrinkage rule using an attention-based Long-Short-Term-Memory (LSTM) network, allowing a formal selection of reference portfolios where the network forecasts future performance based on predetermined out-of-sample monthly certainty equivalent return. We reduce the dimension of successful candidates and then linearly combine them. When nested within a minimum-variance, Bayes-Stein shrinkage, Black-Litterman portfolio framework with four types of weight constraints based on no-short-selling, upper, lower-generalized variance-based restrictions, our approach delivers a clear improvement over the baseline sample-based minimum-variance portfolio and claims superiority over 11 GARCH models used to forecast covariances, as well as a minimum-variance combination of all dynamic optimization models. We provide an illustrative example based on optimal diversification across hedge fund strategies. Robustness checks show our application of sparse covariance dominates the use of a dimension reduction algorithm for Wishart covariance forecasting.

Keywords: Investment analysis, portfolio management, machine learning, deep learning, parameter uncertainty

JEL Classification: G11

Suggested Citation

Huang, Xinyu and Guidolin, Massimo and Platanakis, Emmanouil and Newton, David, Dynamic Portfolio Management with Machine Learning (January 30, 2021). Available at SSRN: https://ssrn.com/abstract=3770688 or http://dx.doi.org/10.2139/ssrn.3770688

Xinyu Huang

University of Bath - School of Management ( email )

Claverton Down
Bath, BA2 7AY
United Kingdom

Massimo Guidolin

Bocconi University - Department of Finance ( email )

Via Roentgen 1
Milano, MI 20136
Italy

Emmanouil Platanakis (Contact Author)

University of Bath - School of Management ( email )

Claverton Down
Bath, BA2 7AY
United Kingdom

David Newton

University of Bath - School of Management ( email )

Claverton Down
Bath, BA2 7AY
United Kingdom

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

Paper statistics

Downloads
459
Abstract Views
908
rank
75,437
PlumX Metrics