Cross-Asset Momentum Spillovers and Network-Based Futures Trading
Summary
The paper studies whether momentum information in one futures market can help predict momentum in others. It builds a network from price-derived momentum features across 64 continuously traded contracts in commodities, equities, bonds, and currencies, avoiding the need to specify company links or other economic relationships in advance.
A linear, interpretable graph-learning method estimates connections among the contracts, and the resulting network informs a multi-asset momentum strategy. The paper reports that, after volatility scaling, the strategy achieved a 1.5 Sharpe ratio and 22% annual return over 2000–2022. These findings are presented as empirical support for using cross-market momentum links in portfolio signals. The document provides only headline performance figures; it does not describe transaction costs, implementation details, or robustness tests, so the results’ practical limits cannot be assessed from this summary alone.
Key ideas
- Momentum risk premia may propagate between assets with similar momentum behavior.
- A learned network can represent cross-market momentum links using price features alone.
- The analysis covers 64 futures contracts across four broad asset classes.
- A linear graph-learning model is used to keep the inferred connections interpretable.
- The network informs a volatility-scaled strategy with reported performance over 2000–2022.
Tags
Full text
# Network Momentum across Asset Classes # Network Momentum across Asset Classes We investigate the concept of network momentum, a novel trading signal derived from momentum spillover across assets. Initially observed within the confines of pairwise economic and fundamental ties, such as the stock-bond connection of the same company and stocks linked through supply-demand chains, momentum spillover implies a propagation of momentum risk premium from one asset to another. The similarity of momentum risk premium, exemplified by co-movement patterns, has been spotted across multiple asset classes including commodities, equities, bonds and currencies. However, studying the network effect of momentum spillover across these classes has been challenging due to a lack of readily available common characteristics or economic ties beyond the company level. In this paper, we explore the interconnections of momentum features across a diverse range of 64 continuous future contracts spanning these four classes. We utilise a linear and interpretable graph learning model with minimal assumptions to reveal the intricacies of the momentum spillover network. By leveraging the learned networks, we construct a network momentum strategy that exhibits a Sharpe ratio of 1.5 and an annual return of 22%, after volatility scaling, from 2000 to 2022. This paper pioneers the examination of momentum spillover across multiple asset classes using only pricing data, presents a multi-asset investment strategy based on network momentum, and underscores the effectiveness of this strategy through robust empirical analysis.
Shown in full with attribution under the source's licence. Licence: abstract CC0
This summary was written by Stratmill's research agent from the original; it is not a copy of the source.