Hierarchical Graph Learning for Commodity Calendar Spreads
Summary
The study models commodity futures as a hierarchy: underlying assets form one level, while individual contracts form another. Relationships connect assets within each level, and cross-level links tie contracts to their underlying markets. A hierarchical graph learning model uses these relationships, including maturity-dependent connections among contracts, to predict futures price movements and generate calendar spread positions. The paper also describes a method for translating model predictions into spread trades.
The authors analytically argue that calendar spreads can have higher information ratios and lower variance and delta than long-only strategies. Tests on commodity futures traded through CME Group report better prediction and trading performance than benchmark models, and identify maturity links as useful to prediction. The reported findings support the proposed statistical arbitrage approach, but the supplied summary gives no sample period, costs, implementation details, or out-of-sample robustness evidence, limiting assessment of real-world performance.
Key ideas
- The model represents underlying assets and individual futures contracts as linked graph levels.
- Maturity-dependent relationships are used to predict futures price movements.
- Predictions are converted into positions in calendar spreads.
- The authors report improved prediction and trading results against benchmark models in CME Group futures.
- The supplied description does not specify trading costs or robustness across other periods and markets.
Tags
Full text
# Hierarchical Graph Learning for Calendar Spread Strategies in Commodity Futures Markets # Hierarchical Graph Learning for Calendar Spread Strategies in Commodity Futures Markets Commodity futures can be represented hierarchically, with underlying assets at the upper level and individual futures contracts at the lower level. Entities at each level can be connected by edges reflecting inherent correlations, with cross-level edges capturing contract-to-underlying asset connections. Building on our observations of these structures, we propose a hierarchical graph learning approach for calendar spread (CS) strategies in commodity futures markets, addressing two significant gaps in the machine-learning literature: (i) the absence of learning-based methods for CS strategies in futures markets, and (ii) the lack of consideration of maturity-dependent interrelationships across commodity futures. We first establish the efficacy of CS strategies by analytically showing that CS strategies can possess higher risk-adjusted returns, measured by the information ratio, and lower risk, measured by variance and delta, than long-only strategies. We then introduce a method to convert learning-based predictions into CS positions. Next, we develop a hierarchical graph learning method that predicts futures price movements by utilizing the maturity-dependent interrelationships, thereby yielding a CS trading algorithm. Empirical results on commodity futures markets traded on the Chicago Mercantile Exchange Group demonstrate that our method outperforms benchmark models in both prediction and trading performance. We find that maturity-dependent interrelationships across commodity futures are instrumental in prediction and that CS trading based on hierarchical graph learning is effective for statistical arbitrage.
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.