A Pattern New in Every Moment: The Temporal Clustering of Markets for Crude Oil, Refined Fuels, and Other Commodities

The identification of critical periods and business cycles contributes significantly to the analysis of financial markets and the macroeconomy. Financialization and cointegration place a premium on the accurate recognition of time-varying volatility in commodity markets, especially those for crude oil and refined fuels. This article seeks to identify critical periods in the trading of energy-related commodities as a step toward understanding the temporal dynamics of those markets. This article proposes a novel application of unsupervised machine learning. A suite of clustering methods, applied to conditional volatility forecasts by trading days and individual assets or asset classes, can identify critical periods in energy-related commodity markets. Unsupervised machine learning achieves this task without rules-based or subjective definitions of crises. Five clustering methods—affinity propagation, mean-shift, spectral, k-means, and hierarchical agglomerative clustering—can identify anomalous periods in commodities trading. These methods identified the financial crisis of 2008–2009 and the initial stages of the COVID-19 pandemic. Applied to four energy-related markets—Brent, West Texas intermediate, gasoil, and gasoline—the same methods identified additional periods connected to events such as the September 11 terrorist attacks and the 2003 Persian Gulf war. t-distributed stochastic neighbor embedding facilitates the visualization of trading regimes. Temporal clustering of conditional volatility forecasts reveals unusual financial properties that distinguish the trading of energy-related commodities during critical periods from trading during normal periods and from trade in other commodities in all periods. Whereas critical periods for all commodities appear to coincide with broader disruptions in demand for energy, critical periods unique to crude oil and refined fuels appear to arise from acute disruptions in supply. Extensions of these methods include the definition of bull and bear markets and the identification of recessions and recoveries in the real economy.

Clustering commodity markets in space and time: Clarifying returns, volatility, and trading regimes through unsupervised machine learning

Unsupervised machine learning can interpret logarithmic returns and conditional volatility in commodity markets. This article applies machine learning in order to visualize and interpret log returns and conditional volatility in commodities trading. We emphasize two classes of unsupervised learning methods: clustering and manifold learning for the reduction of dimensionality. We source daily prices from September 18, 2000 through July 31, 2020, for precious metals, base metals), energy commodities and agricultural commodities. Our results highlight that at the very least, returns-based clusters conform more closely to traditional boundaries between precious metals, base metals, fuels, temperate-climate agricultural commodities, and tropical agricultural commodities. On the other hand, volatility-based clustering succeeds in identifying periods of extreme market distress, such as the global financial crisis of 2008–09 and the Covid-19 pandemic.