International Journal Evolving Sustainable and Renewable Energy Solutions
An Agent-Based Approach to Forecasting Renewable Energy Stock Prices: A Review of Recent Literature (2023â2025)Solutions
Abstract
Heng Chen
The renewable energy sector has rapidly become a central component of the global transition toward sustainability, attracting unprecedented investment and attention from policymakers, financial institutions, and researchers. However, forecasting renewable energy stock prices remains a complex task due to their high volatility, policy dependence, and sensitivity to technological and environmental changes. This paper provides a comprehensive review of recent developments (2023–2025) in applying Agent-Based Modeling (ABM) to financial forecasting, with a specific focus on renewable energy stock markets. The study highlights how ABM captures heterogeneous agent behavior, adaptive learning, and emergent market phenomena that traditional econometric models fail to represent. Recent advances, such as the integration of multi-agent deep reinforcement learning and hybrid ABM–machine learning frameworks, have significantly enhanced the predictive and explanatory power of ABM. The review also discusses ABM applications in energy market dynamics and sustainable finance, emphasizing their relevance for modeling policy-driven, ESG- oriented investor behavior. Finally, it outlines the major challenges—including calibration, data integration, and inter- market modeling—and proposes future directions for developing robust, AI-augmented ABMs. The findings underscore the growing importance of ABM as a methodological foundation for forecasting renewable energy stock prices in an increasingly complex, policy-sensitive global market.