Investigating the Transition Dimension in Climate Investing with Natural Language Processing

Contents:

• Investigating the Transition Dimension in Climate Investing with Natural Language Processing
  • Financing the Transition: the Hidden Dimension in Paris-Aligned Benchmarks
  • Our Approach: a Text-Based Transition Investing Methodology
• A Green Taxonomy
  • The EU Taxonomy
  • Green, Brown or Mixed Taxonomy?
  • Our Approach: A Mixed Taxonomy
• Using Business Description for a Firm-Level Estimate of Greeness
  • Embeddings with a Sentence Transformer Model
  • Cosine Similarity
  • Greeness Measure
  • Python Implementation & Results
• Transition Portfolio
  • Benchmark Greeness
  • Portfolio’s Excess Greeness and Tracking Error
  • Transition Investing Objectives
  • Targeting a Specific Greeness Improvement
  • TE and Excess Greeness Trade-Off
• Conclusion
• References