Investigating the causal relationship between electricity pricing policy and CO emission: An application of machine learning-driven metalearners.
Journal:
Journal of environmental management
PMID:
40086281
Abstract
Investigating the causal relationship between electricity pricing policies and CO emissions is vital for crafting effective climate strategies, as it reveals how pricing mechanisms can inadvertently influence environmental outcomes. So, the paper utilizes the Causal Machine Learning (CausalML) statistical approach to examine how electricity pricing policies affect carbon dioxide (CO) emissions within the household sector. The study utilizes the Causal Machine Learning (CausalML) statistical approach to examine how electricity pricing policies affect carbon dioxide (CO) emissions within the household sector. To achieve this, it analyzes hourly data collected from 2011 to 2013. The analysis explores the causal relationship between potential outcomes and treatment effects, with changes in pricing policies serving as the treatment. This examination questions the traditional views on incentive-based electricity pricing. The results indicate that implementing such policies might unintentionally raise CO intensity. Furthermore, a contemporary statistical method involving a machine learning-based meta-algorithm is incorporated to deepen the causal analysis. Policymakers could encourage electricity consumers and producers by promoting the use of solar panels.