Paper: arXiv 2601.19321

Authors: Fredy Pokou, Jules Sadefo Kamdem, Kpante Emmanuel Gnandi

Abstract

This paper investigates whether structural econometric models can rival machine learning in forecasting energy–macro dynamics while retaining causal interpretability. Using monthly data from 1999 to 2025, we develop a unified framework that integrates Time-Varying Parameter Structural VARs (TVP-SVAR) with advanced dependence structures, including DCC-GARCH, t-copulas, and mixed Clayton–Frank–Gumbel copulas. These models are empirically evaluated against leading machine learning techniques Gaussian Process Regression (GPR), Artificial Neural Networks, Random Forests, and Support Vector Regression across seven macro-financial and energy variables, with Brent crude oil as the central asset. The findings reveal three major insights. First, TVP-SVAR consistently outperforms standard VAR models, confirming structural instability in energy transmission channels. Second, copula-based extensions capture non-linear and tail dependence more effectively than symmetric DCC models, particularly during periods of macroeconomic stress. Third, despite their methodological differences, copula-enhanced econometric models and GPR achieve statistically equivalent predictive accuracy (t-test p = 0.8444). However, only the econometric approach provides interpretable impulse responses, regime shifts, and tail-risk diagnostics. We conclude that machine learning can replicate predictive performance but cannot substitute the explanatory power of structural econometrics. This synthesis offers a pathway where AI accuracy and economic interpretability jointly inform energy policy and risk management.

Complexity vs Empirical Score

  • Math Complexity: 7.5/10
  • Empirical Rigor: 8.5/10
  • Quadrant: Holy Grail — high math complexity, high empirical rigor

Why this score: This paper presents a strong synthesis of theoretical econometrics and empirical machine learning by combining TVP-SVAR, DCC-GARCH, and mixed copula models with non-parametric ML techniques like GPR. The empirical validation is rigorous, using monthly macro-financial and energy data spanning over two decades (1999–2025) and incorporating statistical significance testing (p-values) to evaluate predictive parity.

Research Flowchart

  flowchart TD
    A[Research Goal: Evaluate Predictive Accuracy vs. Interpretability in Energy Markets] --> B[Data Inputs: Monthly Macro-Financial & Energy Data 1999-2025, Brent Crude]
    B --> C[Methodology: Compare Econometric Models vs. Machine Learning]
    C --> D[Econometric Models: TVP-SVAR, DCC-GARCH, t-Copulas, Mixed Copulas]
    C --> E[Machine Learning Models: GPR, ANN, Random Forests, SVR]
    D & E --> F[Empirical Evaluation & Predictive Accuracy Comparison]
    F --> G[Key Outcomes: Copula TVP-SVAR & GPR Statistically Equivalent Accuracy p=0.8444<br/>Only Econometric Approach Retains Interpretability & Tail-Risk Diagnostics]