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

Abstract

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.

Hints of Earlier and Other Creation: Unsupervised Machine Learning in Financial Time-Series Analysis

“…A single method of manifold learning-t-distributed stochastic neighbor embedding (t-SNE)-facilitates the visualization of clusters among commodity markets [20][21][22]. A comprehensive discussion of those five clustering methods and t-SNE appears in [3] (pp. 12-14).…”

“…A sequel to [2], "A Pattern New in Every Moment," used temporal clustering to identify critical periods in energy-related commodity markets [3]. That article applied a suite of clustering methods to the transpose of the time-series matrix evaluated in [2].…”

“…By focusing on critical periods identified by temporal clustering, this study's novel hybrid clustering method reveals the This study proposes further elaborations in unsupervised machine learning. By combining the ontological (or spatial) approach to clustering of [2] with the temporal approach of [3], this study makes its own distinctive contribution to the application of unsupervised machine learning to financial time series. Ontological clustering, conditioned upon the identification of structural breaks and other critical periods, should reveal information about co-movement among asset classes and discrete assets as markets shift between normal and extraordinary states.…”

Food price dynamics and regional clusters: machine learning analysis of egg prices in China

“…, 2021, 2022). For instance, Chen and Rehman (2021) employed five clustering methods including K-means and hierarchical clustering to identify critical periods in energy markets, analyze trades and understand temporal volatility in financial markets. Conradt et al.…”

Emerging Trends in Energy Economics

“…Ioannidis et al in [2] examine the recently introduced Target Model, its application in the wholesale electricity market of Greece and its impact on electricity prices. Chen and Rehman in [3] identify the critical periods in the trading of energy-related commodities employing an unsupervised Machine Learning framework. Balashova and Serletis in [4] uncover hidden linkages between the oil price uncertainty, the total factor productivity (TFP) growth, and the critical indicators of knowledge production and associated spillovers.…”