A new research paper proposes a method to combat corporate greenwashing by using algorithmic verification of emissions data. The study leverages U.S. SEC financial data and EPA greenhouse gas registries to create a baseline of physical emissions, identifying a metric called Conformal-Weighted Continuous Divergence (CWCD). This metric quantifies the discrepancy between self-reported emissions and the algorithmic baseline, revealing that companies with significant divergence experience lower market valuations and profitability, suggesting that markets actively penalize environmental deception as a sign of mismanagement. AI
IMPACT Introduces a novel algorithmic auditing framework that could enable regulators and asset managers to better detect and penalize corporate greenwashing.
RANK_REASON Academic paper published on arXiv detailing a new methodology for verifying corporate emissions data. [lever_c_demoted from research: ic=1 ai=1.0]
- arXiv
- Conformal Machine Learning
- Conformal-Weighted Continuous Divergence (CWCD)
- electronic health records
- greenwashing
- Mondrian conformal prediction
- Rennes
- Tobin's q
- United States Secretary of State
AI-generated summary · Google Gemini · from 1 sources. How we write summaries →
