United StatesFinance and insurance2023 – ongoingIFC
MALENA machine learning ESG analyst
IFC's machine learning ESG analyst cut due diligence document review from weeks to days
Problem
IFC investment teams had to assess environmental, social and governance risk by reading large volumes of unstructured company documents by hand. This was slow.
Approach
IFC built MALENA, a machine learning ESG analyst that uses natural language processing, sentiment analysis and named entity recognition on Databricks. It extracts ESG insights from text for in-house due diligence. IFC plans to offer it to outside users.
Results
Takeaway
Machine reading of text can turn a weeks-long review task into a days-long one. The IFC page gives no accuracy comparison with human reviewers.
Categories
- Size
- Large enterprise
- Industry
- Finance and insurance
- Business function
- Finance, risk and legal
- Innovation type
- Process innovation
- AI technology
- Generative AIPredictive analytics and ML
- Adoption
- Built in-house
- Evidence
- Vendor case study
Sources
Source summaries
Databricks describes IFC's MALENA platform, which extracts ESG insights from unstructured documents. It reports analysis of 19,000 sentences per minute, a 950x increase, and due diligence document analysis cut from weeks to days.
Full details are in the original sources.