Comparative Evaluation of Modern Deep Learning Methodologies for Portfolio Optimization

TL;DR

This paper evaluates various deep learning architectures, including GNNs, DRL, Transformers, and Autoencoders, for portfolio optimization, demonstrating that hybrid models outperform standalone approaches in risk management and return metrics.

Contribution

It introduces a comprehensive framework integrating advanced deep learning models with traditional financial methods, highlighting the benefits of hybrid approaches for portfolio optimization.

Findings

Hybrid models like Transformer+GNN outperform standalone models in stability and risk control.

MVO with well-calibrated inputs achieves highest cumulative return and Sharpe ratio.

Autoencoders behave similarly to equal-weight strategies, indicating limited dynamic adaptation.

Abstract

This study proposes a portfolio optimization framework that integrates advanced deep learning architectures with traditional financial models to enhance risk-adjusted performance. Using historical data from 2015-2023 across equities, ETFs, and bonds, the research evaluates the predictive power of Graph Neural Networks (GNNs), Deep Reinforcement Learning (DRL), Transformers, and Autoencoders. The models jointly address covariance estimation, return forecasting, dynamic asset allocation, and dimensionality reduction. Hybrid approaches such as Transformer+GNN and Autoencoder+DRL are also explored to capture both relational and temporal market structures. Performance is assessed through backtesting using metrics including volatility, cumulative return, maximum drawdown, annualized return, and Sharpe ratio across seven strategies, including Equal-Weighted, 60/40 allocation, and Mean-Variance Optimization (MVO). Results show that hybrid models provide superior stability and risk control, with Transformer+GNN achieving the lowest volatility and drawdown. MVO, when paired with well-calibrated inputs, delivers the highest cumulative return and Sharpe ratio, highlighting the continued relevance of traditional methods. Standalone DRL underperforms due to limited structural awareness, while Autoencoders exhibit behavior similar to Equal-Weight strategies, emphasizing the need for dynamic policy learning. These findings align with existing literature on relational modeling and feature compression in finance. Overall, the study demonstrates that combining deep learning with financial theory yields robust and adaptive portfolio strategies and suggests exploring latent representations within traditional optimization frameworks to improve scalability and performance.