DeepUnifiedMom: Unified Time-series Momentum Portfolio Construction via Multi-Task Learning with Multi-Gate Mixture of Experts

TL;DR

DeepUnifiedMom is a deep learning framework that unifies time-series momentum across multiple asset classes using multi-task learning and mixture of experts, leading to superior portfolio performance.

Contribution

It introduces a novel multi-task learning approach with a multi-gate mixture of experts to construct unified momentum portfolios across diverse assets.

Findings

Consistently outperforms benchmark models after transaction costs

Effective in capturing momentum across multiple asset classes

Enhances risk-adjusted returns in portfolio management

Abstract

This paper introduces DeepUnifiedMom, a deep learning framework that enhances portfolio management through a multi-task learning approach and a multi-gate mixture of experts. The essence of DeepUnifiedMom lies in its ability to create unified momentum portfolios that incorporate the dynamics of time series momentum across a spectrum of time frames, a feature often missing in traditional momentum strategies. Our comprehensive backtesting, encompassing diverse asset classes such as equity indexes, fixed income, foreign exchange, and commodities, demonstrates that DeepUnifiedMom consistently outperforms benchmark models, even after factoring in transaction costs. This superior performance underscores DeepUnifiedMom's capability to capture the full spectrum of momentum opportunities within financial markets. The findings highlight DeepUnifiedMom as an effective tool for practitioners looking to exploit the entire range of momentum opportunities. It offers a compelling solution for improving risk-adjusted returns and is a valuable strategy for navigating the complexities of portfolio management.