Dynamic ETF Portfolio Optimization Using enhanced Transformer-Based Models for Covariance and Semi-Covariance Prediction(Work in Progress)

TL;DR

This paper proposes a novel ETF portfolio optimization method using Transformer models to predict dynamic covariance and semi-covariance matrices, improving risk management and performance in volatile markets.

Contribution

It introduces Transformer-based models for real-time prediction of covariance and semi-covariance matrices, enhancing portfolio optimization beyond traditional static methods.

Findings

Transformer predictions improve portfolio performance.

Semi-covariance matrix outperforms covariance in volatile markets.

Risk-adjusted returns are higher using the semi-covariance approach.

Abstract

This study explores the use of Transformer-based models to predict both covariance and semi-covariance matrices for ETF portfolio optimization. Traditional portfolio optimization techniques often rely on static covariance estimates or impose strict model assumptions, which may fail to capture the dynamic and non-linear nature of market fluctuations. Our approach leverages the power of Transformer models to generate adaptive, real-time predictions of asset covariances, with a focus on the semi-covariance matrix to account for downside risk. The semi-covariance matrix emphasizes negative correlations between assets, offering a more nuanced approach to risk management compared to traditional methods that treat all volatility equally. Through a series of experiments, we demonstrate that Transformer-based predictions of both covariance and semi-covariance significantly enhance portfolio performance. Our results show that portfolios optimized using the semi-covariance matrix outperform those optimized with the standard covariance matrix, particularly in volatile market conditions. Moreover, the use of the Sortino ratio, a risk-adjusted performance metric that focuses on downside risk, further validates the effectiveness of our approach in managing risk while maximizing returns. These findings have important implications for asset managers and investors, offering a dynamic, data-driven framework for portfolio construction that adapts more effectively to shifting market conditions. By integrating Transformer-based models with the semi-covariance matrix for improved risk management, this research contributes to the growing field of machine learning in finance and provides valuable insights for optimizing ETF portfolios.