Electricity Market Predictability: Virtues of Machine Learning and Links to the Macroeconomy

TL;DR

This paper compares machine learning models for forecasting Singapore's electricity prices, demonstrating their ability to capture non-linearity and complexity, and linking predictability to macroeconomic regimes and economic gains.

Contribution

It provides a comprehensive empirical analysis of 15 ML models and ensemble methods for electricity price forecasting, highlighting their virtues and macroeconomic linkages.

Findings

ML models effectively capture non-linearity and complexity.

Ensemble methods improve prediction accuracy, especially with penalized correlation.

Predictability varies across macro regimes, with economic gains achievable.

Abstract

With stakeholder-level in-market data, we conduct a comparative analysis of machine learning (ML) for forecasting electricity prices in Singapore, spanning 15 individual models and 4 ensemble approaches. Our empirical findings justify the three virtues of ML models: (1) the virtue of capturing non-linearity, (2) the complexity (Kelly et al., 2024) and (3) the l2-norm and bagging techniques in a weak factor environment (Shen and Xiu, 2024). Simulation also supports the first virtue. Penalizing prediction correlation improves ensemble performance when individual models are highly correlated. The predictability can be translated into sizable economic gains under the mean-variance framework. We also reveal significant patterns of time-series heterogeneous predictability across macro regimes: predictability is clustered in expansion, volatile market and extreme geopolitical risk periods. Our feature importance results agree with the complex dynamics of Singapore's electricity market after de regulation, yet highlight its relatively supply-driven nature with the continued presence of strong regulatory influences.