Clean energy stock price forecasting and response to macroeconomic variables: A novel framework using Facebook's Prophet, NeuralProphet and explainable AI

Abstract

The clean energy market analysis has seen a strong surge in the post-Paris agreement owing to its undeniable environmental sustainability. The present work investigates the predictability of clean energy investment in the US market by selecting eight sectoral stock indices. The predictive exercise is carried out separately during pre-COVID-19 and COVID-19 timelines to draw key behavioral aspects of the underlying sectors. After scrutiny of previous research, we identify a set of technical and macroeconomic variables as explanatory constructs. We then utilize Facebook's Prophet and NeuralProphet to find future figures for the clean energy indices. Finally, Explainable Artificial Intelligence (XAI) is used to draw deeper insights into the contribution patterns of the constituent explanatory variables and obtain their relative importance. The findings suggest that the future movements of the sectoral clean energy assets can be predicted with a very high level of accuracy. Also, the predictability marginally improves during the COVID-19 pandemic despite the unprecedented uncertainty. Technical indicators appear to be the dominant features, while market sentiment and fear exert significant influence.