Abstract
We explore the modern application of deep learning techniques in portfolio construction, presenting innovative methodologies that significantly enhance traditional investment strategies. Central to this research are three advanced frameworks that leverage deep learning to optimize financial portfolios.
The first framework introduces a diversified risk-adjusted TSMOM strategy utilizing multi-task learning. This approach simultaneously optimizes portfolio construction and volatility forecasting, resulting in improved portfolio performance by learning both momentum signals and volatility estimators. Experimental results involving a diversified portfolio of continuous futures contracts demonstrate that this method outperforms existing TSMOM strategies.
The second framework employs a multi-task learning model with a multi-gate mixture of experts to optimize momentum portfolios across multiple timeframes. This model excels over benchmarks across various asset classes, effectively capturing complex momentum dynamics in equity indexes, fixed income, foreign exchange, and commodities. Extensive backtesting highlights its capacity to enhance risk-adjusted returns, underscoring its practical utility for portfolio management.
The third framework presents an adaptive sparse Transformer model designed for index tracking. By combining sparse modeling with deep learning, this framework optimizes passive investment strategies. Backtesting spanning from 2005 to 2024 reveals that it delivers higher excess returns and lower tracking errors compared to existing models, showcasing the effectiveness of this approach in refining index tracking methodologies.
Lastly, we introduce the CurveMMOE model, a deep-learning framework for trading commodity futures curves. This model integrates multi-task learning with a Mixture of Expert architecture, outperforming traditional methods on risk-adjusted returns.
These frameworks contribute significantly to portfolio construction by harnessing the power of deep learning techniques. They provide investment practitioners with innovative approaches to improve financial performance, particularly in challenging market environments. This research advances our understanding of deep learning in finance and offers practical strategies for real-world investment scenarios.
Speaker’s Profile
Joel Ong is a PhD candidate at the Singapore University of Technology and Design (SUTD), specializing in the application of deep learning techniques in portfolio construction and financial modeling. Prior to pursuing his PhD, he worked as a quantitative researcher, focusing on developing advanced signal generation methods and innovative portfolio construction strategies. He holds an undergraduate degree from SUTD, where he majored in Information Systems Technology and Design (ISTD).
