Learning to Learn Financial Networks for Optimising Momentum Strategies

TL;DR

This paper introduces L2GMOM, an end-to-end neural network framework that learns financial networks and optimizes momentum trading strategies simultaneously, improving portfolio performance and risk management.

Contribution

It presents a novel neural network model derived from algorithm unrolling that jointly learns network structures and trading signals, addressing limitations of traditional separate approaches.

Findings

Achieved a Sharpe ratio of 1.74 over 20 years in backtests.

Significantly improved portfolio profitability and risk control.

Demonstrated flexibility with various portfolio performance loss functions.

Abstract

Network momentum provides a novel type of risk premium, which exploits the interconnections among assets in a financial network to predict future returns. However, the current process of constructing financial networks relies heavily on expensive databases and financial expertise, limiting accessibility for small-sized and academic institutions. Furthermore, the traditional approach treats network construction and portfolio optimisation as separate tasks, potentially hindering optimal portfolio performance. To address these challenges, we propose L2GMOM, an end-to-end machine learning framework that simultaneously learns financial networks and optimises trading signals for network momentum strategies. The model of L2GMOM is a neural network with a highly interpretable forward propagation architecture, which is derived from algorithm unrolling. The L2GMOM is flexible and can be trained with diverse loss functions for portfolio performance, e.g. the negative Sharpe ratio. Backtesting on 64 continuous future contracts demonstrates a significant improvement in portfolio profitability and risk control, with a Sharpe ratio of 1.74 across a 20-year period.