Graphical Models for Financial Time Series and Portfolio Selection

TL;DR

This paper explores the use of various graphical models to improve portfolio optimization by capturing dynamic patterns in financial time series, leading to better risk-adjusted returns compared to traditional methods.

Contribution

It introduces multiple graphical modeling techniques for portfolio construction, demonstrating their effectiveness in capturing temporal dependencies and outperforming baseline strategies.

Findings

Graphical models often outperform baseline methods.

Portfolios using these models show higher returns with lower risk.

Models outperform the S&P 500 index in many cases.

Abstract

We examine a variety of graphical models to construct optimal portfolios. Graphical models such as PCA-KMeans, autoencoders, dynamic clustering, and structural learning can capture the time varying patterns in the covariance matrix and allow the creation of an optimal and robust portfolio. We compared the resulting portfolios from the different models with baseline methods. In many cases our graphical strategies generated steadily increasing returns with low risk and outgrew the S&P 500 index. This work suggests that graphical models can effectively learn the temporal dependencies in time series data and are proved useful in asset management.