Forecasting Oil Consumption: The Statistical Review of World Energy Meets Machine Learning

TL;DR

The paper develops a high-dimensional framework to forecast oil consumption by identifying a small set of dominant countries using a non-symmetric concentration-matrix approach estimated with LASSO and OCMT. It finds a global driver in the United States and regional hubs in France and Japan, whose inclusion improves forecast accuracy over AR benchmarks, especially during global shocks. The method demonstrates robustness to factor controls (CCE) and yields insights into transmission via a SVAR, suggesting practical applicability for other macro variables with network structure. Overall, a parsimonious set of dominant drivers can capture most oil-demand dynamics and offer actionable improvements for forecasting and policy analysis.

Abstract

This paper studies whether a small set of dominant countries can account for most of the dynamics of regional oil demand and improve forecasting performance. We focus on dominant drivers within the OECD and a broad GVAR sample covering over 90\% of world GDP. Our approach identifies dominant drivers from a high-dimensional concentration matrix estimated row by row using two complementary variable-selection methods, LASSO and the one-covariate-at-a-time multiple testing (OCMT) procedure. Dominant countries are selected by ordering the columns of the concentration matrix by their norms and applying a criterion based on consecutive norm ratios, combined with economically motivated restrictions to rule out pseudo-dominance. The United States emerges as a global dominant driver, while France and Japan act as robust regional hubs representing European and Asian components, respectively. Including these dominant drivers as regressors for all countries yields statistically significant forecast gains over autoregressive benchmarks and country-specific LASSO models, particularly during periods of heightened global volatility. The proposed framework is flexible and can be applied to other macroeconomic and energy variables with network structure or spatial dependence.

Figures (14)

• Figure 1: Column norm shares and network graphs - OECD
• Figure 2: Column norm shares and network graphs - GVAR
• Figure 3: Cross-sectional Diebold-Mariano Test statistics – AR benchmark
• Figure 4: Time series Diebold-Mariano test statistics for aggregate oil consumption - AR benchmark
• Figure 5: Contemporaneous correlation matrices in all specifications