Winter 2025

Extending the popular heterogeneous autoregressive (HAR) model with additional information channels to forecast realized volatility of WTI futures prices, the authors show that machine learning-generated forecasts provide better forecasting quality and that portfolios that are constructed with these forecasts outperform their competing models resulting in economic gains. Analyzing the selection process, they show that information channels vary across forecasting horizons. Variable selection produces clusters and provides evidence that there are structural changes with regard to the significance of information channels.

This study introduces media emotion intensity—measuring the proportion of emotional versus factual content in news—as a novel predictor of commodity futures returns. Emotion intensity measures the proportion of emotional content relative to factual content in media news. The media emotion intensity factor generates an economically significant annual premium of approximately 13%, even after accounting for transaction costs. This premium is more pronounced for commodities with low media coverage, high momentum, high basis-momentum, high hedging pressure, and backwardation. Emotion intensity significantly predicts the trading tendencies of both commercial and non-commercial traders and the cross-section of commodity futures returns at both portfolio and individual levels. The study also finds that media emotion intensity predicts future commodities’ sentiment. Further, other commonly considered risk sources cannot subsume the predictability of the media emotion intensity factor.

This paper investigates the ability of a ChatGPT-based indicator to forecast excess returns of a commodity futures index. Using ChatGPT to extract information from over 2.5 million articles from nine international newspapers, the authors demonstrate that their constructed commodity news ratio index significantly predicts future commodity returns, both in-sample and out-of-sample. Furthermore, it outperforms traditional textual analysis methods while indicating economic significance within an asset allocation framework. The results highlight the critical role of ChatGPT in forecasting commodity market dynamics and provide valuable insights for both financial market participants and researchers.

The authors present a unified framework for pricing calendar spread options on energy commodities under affine models featuring stochastic volatility, jumps, and the Samuelson effect. Expressions for the joint characteristic function of log-futures prices are derived, enabling efficient calibration and valuation. An empirical analysis, across WTI crude oil, HH natural gas, and ULSD heating oil shows that stochastic volatility models consistently outperform others. Jumps enhance short-term fit, while volatility dynamics matter more at longer maturities. The Black model remains competitive for short- and mid-term contracts.

Building on the influential Gibson and Schwartz (1990) and Schwartz and Smith (2000) two-factor models for commodity spot prices, this paper extends the framework to incorporate stochastic volatility and time-varying correlation through a Wishart variance-covariance matrix process. This generalization provides joint characteristic functions for both the state variables and their variance-covariance matrices, offering a richer description of the dynamics of volatility and correlation in commodity markets. While the original models are well known for tractably capturing the term structure of futures prices and implied volatility, the extended versions further account for volatility smiles and relax the restrictive assumption of constant correlation, facilitating empirical analysis via filtering techniques.

This article examines whether data from remote sensing satellites can be used to predict lithium mine output. The authors use pixel classification of land cover to measure long-term mine expansion and nightly light emissions to measure short-term operational activities. They find a strong correlation between satellite data in one period and individual lithium mine production volumes in the following period. Our rapid and cost-effective method of forecasting lithium mine production can help decision-makers in companies that rely on lithium, and policymakers seeking to ensure adequate lithium supplies in their countries.

The article provides unique quantitative insights about highly secretive and poorly understood speculation in the oil market. To demystify the behavior of speculators, the authors look at the problem from several different angles. First, they explain how the presence of the large over-the-counter (OTC) oil derivatives market leads to mischaracterization of traditional hedgers and speculators. They then explain what makes oil speculation special and different from speculation across many other commodities. Consequently, the authors identify the winners and the losers in the oil futures market. To model the behavior of the winners which they associate with fast-moving quantitative hedge funds, they develop a novel framework based on a simple neural-network algorithm. The authors conclude by analyzing a popular investment strategy of following the winners, or the hedge-funds’ flows.

The day-to-day world of crude oil traders is not usually open to outsiders. Few non-specialists appreciate how oil traders approach the markets, what their backgrounds are, and how they make money. This article briefly summarizes a book which brings the oil trading world to vivid life. The book, in turn, introduces the reader to 40 real-life trades or strategies that were carried out by named market participants. The 40 chapters cover different geographies and different crude oil markets, providing an unparalleled insight into how crude oil traders work and think, as well as insight into how the markets have developed over time.

Prior to the Pandemic of 2020, Bitcoin provided a significant degree of diversification to equity-dominated portfolios even if it also was incredibly volatile on its own. There was a marked pattern shift during the Pandemic of 2020, when Bitcoin’s association with equity indexes became exceptionally tight. The flood of emergency stimulus money into the U.S. economy coupled with the Pandemic-triggered work-from-home shift brought a large increase in active retail traders for stocks and cryptocurrencies. Both Bitcoin and equity indexes often traded in similar risk-on, risk-off cycles. As a result, the diversification potential from adding Bitcoin to an equity-dominated portfolio virtually disappeared with the Pandemic pattern shift. This research uses a time-varying parameter (TVP) methodology to identify, quantify, and illustrate pattern shifts between the daily returns of two instruments: Bitcoin and the S&P500® Index. To help appreciate why the pattern shifts occurred, we trace the history of Bitcoin’s association with U.S. equities and build a narrative, taking Bitcoin from its birth and childhood, through its teenager years, to its more mature young adult phase. Each phase had a unique set of properties that were reflected in Bitcoin’s evolving association with equity indexes. Our research suggests that the current association of Bitcoin and equity indexes may not necessarily persist.

Agricultural producers face significant price risk, yet studies consistently find farmers use futures and options much less than predicted by optimal hedging models. Using nationally representative farm-level data, the authors investigate two underexplored factors that can affect the use of exchange-traded derivatives: historical basis risk and cash constraints. They show that corn and soybean farms located in counties that experienced a large, negative change in the corn basis between planting and harvest (a negative basis shock) in the last 5 years are less likely to use futures contracts (6–12 percentage points) and options contracts (3–18 percentage points), but have a greater likelihood of marketing contract use (14–24 percentage points). The authors also find that farms with greater cash constraints (lower cash holdings) are less likely to use futures and options.

In this article, the author begins by reviewing the historical development of modern commodity futures markets. This review is followed by a summary of the factors that determine whether futures contracts succeed or not, namely (1) there must be a commercial need for hedging; (2) a pool of speculators must be attracted to a market; and (3) public policy should (a) not be too unfavorable to futures trading and should (b) prioritize preventing price manipulation via regulation. A key goal of the article is for researchers to be able to distill lessons from the most important mature markets and apply this knowledge to less mature markets as well as to new energy-transition markets.

Dr. Ioannis C. Moutzouris combines several roles at Bayes Business School, City St George’s, University of London, U.K. At Bayes, he serves as (a) the Associate Dean for Engagement, (b) the Onassis Associate Professor in Shipping Finance and Sustainability, and (c) the Shipping and Energy Research Programme Lead. He is also a Co-Investigator in the U.K. National Clean Maritime Research Hub and a Principal Academic Adviser at the U.K. Department for Transport. His main areas of research are in shipping economics and finance.

Chardin Wese Simen is a Professor of Finance at the Management School at the University of Liverpool, U.K. His main research interests include asset pricing, commodity markets, derivatives, and financial econometrics. Professor Wese Simen has published his research in world-leading journals, including the Journal of Econometrics, the Journal of Financial and Quantitative Analysis, Management Science, and the Journal of Money, Credit and Banking. His research has attracted awards and funding from national and international institutions, including the British Academy. He is a member of the editorial boards of the Commodity Insights Digest, the European Journal of Finance, and the Journal of Commodity Markets and is a regular reviewer for leading journals, including the Journal of Business Economics and Statistics, the Journal of Financial and Quantitative Analysis, and Management Science.

Joëlle Miffre is a Professor of Finance at Audencia Business School in France. Her research centers on the pricing and management of commodity futures, with her work published in leading academic journals such as Management Science, Review of Finance, and the Journal of Banking and Finance. She also serves as an Associate Editor for the Journal of Banking and Finance, the Journal of Commodity Markets, and the Journal of Futures Markets. Reflecting the practical relevance of her work, Professor Miffre has advised several financial institutions on topics related to the design, structuring, and pricing of commodity index products.