{"slug":"ifc-assesses-esg-risk-with-ai-powered-malena-platform","url":"https://findausecase.com/use-cases/ifc-assesses-esg-risk-with-ai-powered-malena-platform","title":"IFC assesses ESG risk with AI-powered MALENA platform","description":"The International Finance Corporation (IFC), part of the World Bank Group, built MALENA (Machine Learning ESG Analyst), an AI-powered platform that uses NLP, sentiment analysis and named entity recognition to extract ESG insights from unstructured text such as impact assessments, news articles and sustainability reports at scale. Built on the Databricks Data + AI Platform with GPU computing and MLflow for the ML lifecycle, MALENA analyzes 19,000 sentences per minute (a 950x increase over manual review) and identifies 1,200 ESG risk terms, reducing document analysis time from weeks to days and enabling IFC to offer MALENA to external users as the World Bank Group's first AI as a Service.","company":"International Finance Corporation (IFC)","industry":"Government & Public Sector","aiCapabilities":["Document Intelligence","Generative AI"],"technology":["Databricks Data + AI Platform","MLflow","Azure Data Lake"],"deployment":"Public Cloud","problemStatement":"Previously reliant on manual processes and limited data processing tools, the operationalization of ML models to analyze roughly 21 million pages of text took months to complete, and training and fine-tuning large language models was limited and resulted in frequent failures, with limited cluster choices impacting the ability to optimize model performance.","solutionApproach":"IFC built MALENA, an AI-powered platform that supports the review and analysis of massive amounts of text to identify ESG opportunities and risks; IFC has trained sentiment analysis models to extract insights from across hundreds of thousands of documents, and named entity recognition is used to integrate external data sources and connect news stories to client profiles, all running on the Databricks Data + AI Platform with GPU computing and MLflow for the ML lifecycle.","businessValue":"In-house document analysis times have been reduced from weeks to days for ESG due diligence; MALENA can analyze 19,000 sentences per minute, compared with the average human reader who can only read 15 to 20 sentences per minute, a 950x increase; and IFC has developed 10,000 company profiles and expanded insights for more than 180 markets.","evidence":{"band":"high"},"sourceUrl":"https://www.databricks.com/customers/ifc","dates":{"publishedAt":"2026-09-24T05:49:19.505Z","publishedAtSource":"pipeline","updatedAt":"2026-09-24T05:49:19.505Z"},"license":"Open for reading and citing with a link to https://findausecase.com/use-cases/ifc-assesses-esg-risk-with-ai-powered-malena-platform. Bulk republication requires permission."}