Big portfolio selection by graph-based conditional moments method

TL;DR

This paper introduces a graph-based conditional moments (GRACE) method for large-scale portfolio selection, leveraging advanced neural networks and domain knowledge to improve risk and return estimation for thousands of stocks.

Contribution

The paper proposes a novel GRACE method combining factor-augmented graph convolutional networks and quantiled conditional moments to efficiently estimate higher-order moments for big portfolio selection.

Findings

GRACE outperforms competitors in NASDAQ and NYSE applications.

Incorporating higher-order moments improves portfolio performance.

The method overcomes computational challenges of traditional high-dimensional models.

Abstract

How to do big portfolio selection is very important but challenging for both researchers and practitioners. In this paper, we propose a new graph-based conditional moments (GRACE) method to do portfolio selection based on thousands of stocks or more. The GRACE method first learns the conditional quantiles and mean of stock returns via a factor-augmented temporal graph convolutional network, which guides the learning procedure through a factor-hypergraph built by the set of stock-to-stock relations from the domain knowledge as well as the set of factor-to-stock relations from the asset pricing knowledge. Next, the GRACE method learns the conditional variance, skewness, and kurtosis of stock returns from the learned conditional quantiles by using the quantiled conditional moment (QCM) method. The QCM method is a supervised learning procedure to learn these conditional higher-order moments, so it largely overcomes the computational difficulty from the classical high-dimensional GARCH-type methods. Moreover, the QCM method allows the mis-specification in modeling conditional quantiles to some extent, due to its regression-based nature. Finally, the GRACE method uses the learned conditional mean, variance, skewness, and kurtosis to construct several performance measures, which are criteria to sort the stocks to proceed the portfolio selection in the well-known 10-decile framework. An application to NASDAQ and NYSE stock markets shows that the GRACE method performs much better than its competitors, particularly when the performance measures are comprised of conditional variance, skewness, and kurtosis.