Macroeconomic factors drive clean energy stock returns: comprehensive forecasting framework revealed
image: It shows that macroeconomic predictors dominate the pick-up rate, with UNRATE ranking the highest at 25.64%, followed by GPRH at 20.86%, and TPU at 20.80%. These predictors capture key aspects of labor market dynamics, geopolitical risks, and trade policy uncertainty. This aligns with Baumeister et al. (2022), who demonstrated that macroeconomic indicators, such as unemployment rates and economic activity indices, are robust predictors of energy-related market performance.
Credit: Xinling Liu (Southeast University, China) Binjie Wang and Jianhao Xue (Nanjing University of Aeronautics and Astronautics, China) Qunwei Wang (Nanjing University of Aeronautics and Astronautics, China) Xingyu Dai (Nanjing University of Aeronautics and Astronautics, China) Xuan-Hoa Nghiem (Vietnam National University, Vietnam)
Background and Motivation
As the world transitions toward renewable energy, clean energy stocks have become a pivotal asset class for investors and policymakers alike. However, forecasting their returns remains challenging due to the complex interplay of economic conditions, policy shifts, market sentiment, and climate-related factors. Existing models often focus on limited predictors or traditional financial variables, leaving a gap in understanding the full spectrum of influences on clean energy stock performance. This study addresses that gap by integrating 56 diverse predictors—spanning technical, macroeconomic, climate risk, and financial categories—to build a robust forecasting framework for clean energy stock returns.
Methodology and Scope
Using monthly data from the WilderHill Clean Energy Index (January 2009–December 2023), the study employs advanced shrinkage methods, regularisation techniques, and quantile regression models, including LASSO, Elastic Net, Group LASSO, and Quantile Elastic Net, to handle high-dimensional data and mitigate overfitting. The framework also applies wavelet decomposition to analyse predictor components across short-, medium-, and long-term horizons. Predictors are grouped into four categories: technical indicators (e.g., moving averages, momentum), macroeconomic variables (e.g., CFNAI, unemployment rate), climate risk measures (e.g., climate policy uncertainty, extreme weather), and financial factors (e.g., oil prices, volatility indices).
Key Findings and Contributions
- Macroeconomic Predictors Are Most Influential: Variables such as the Chicago Fed National Activity Index (CFNAI), unemployment rate (UNRATE), and trade policy uncertainty (TPU) consistently show the highest predictive power across all forecasting horizons.
- Climate Risk Factors Are Time-Varying: Climate policy uncertainty and physical risk indicators gain importance during policy shifts and extreme weather events, but are less stable than macroeconomic drivers.
- Technical and Financial Predictors Shine in Volatility: Indicators like on-balance volume (OBV) and momentum are most relevant during periods of market turbulence, offering short-term predictive insights.
- Medium-Term Components Matter Most: Wavelet decomposition reveals that predictors’ medium-term (2–4 month) components contribute most strongly to forecasting accuracy, especially for macroeconomic variables.
- Quantile Elastic Net Outperforms: Among all models tested, the Quantile Elastic Net (Q-EN) model delivers the highest out-of-sample forecasting accuracy, effectively capturing tail risks and non-linear dynamics.
Why It Matters
Accurate forecasting of clean energy stock returns is critical for investors navigating a rapidly evolving sector influenced by policy changes, climate agendas, and global economic shifts. This research not only provides a more nuanced understanding of what drives clean energy markets but also offers a methodological advancement through the integration of diverse predictors and robust regularisation techniques. The findings underscore the importance of adopting multi-factor, time-aware models to improve investment strategies and policy design in the renewable energy transition.
Practical Applications
- Investors & Fund Managers: Can prioritise macroeconomic indicators and medium-term trends when constructing clean energy portfolios, especially during economic uncertainty.
- Policy Makers: May use climate risk predictors to gauge market reactions to environmental policies and tailor interventions to stabilise clean energy investments.
- Financial Analysts: Could incorporate the Q-EN model or group-based regularisation approaches to enhance equity research and risk assessment reports.
- Academic Researchers: May extend the framework to other sustainable asset classes, regional markets, or higher-frequency data to explore additional dynamics.
- Corporate Strategy Teams: In energy firms can monitor key predictors like CFNAI and climate policy indices to inform capital allocation and long-term planning.
Discover high-quality academic insights in finance from this article published in China Finance Review International. Click the DOI below to read the full-text original! Open access for a limited time!