Learning to Learn Financial Networks for Optimising Momentum Strategies
This addresses accessibility and performance issues in financial network momentum strategies for small institutions and academics, though it is incremental as it builds on existing momentum concepts with a new method.
The paper tackles the problem of constructing financial networks for momentum strategies, which traditionally requires expensive data and expertise and treats network construction and portfolio optimization separately. The proposed L2GMOM framework simultaneously learns networks and optimizes trading signals, achieving a Sharpe ratio of 1.74 over 20 years in backtesting.
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.