Presenting the Global Top 100 outstanding projects: MALENA

Published on May 22, 2023

Share this post

After a thorough scientific, ethical, and entrepreneurial review of all projects submitted to the 2022 IRCAI Global Top 100 call, IRCAI has deemed ten submissions as “outstanding” based on their AI integrity, potential impact on the SDGs, business sustainability, and ethical design. One of those ten submissions was MALENA. Earlier this month at our STI Forum side event, we had the opportunity to hear from MALENA’s Product Owner, Florian Skene.

What is MALENA?

MALENA is the International Finance Corporation’s ML-based Environment, Social and Governance (ESG) analyst. Based on Natural Language Processing (NLP), MALENA enables investors to quickly review IFC’s extensive in-house sustainability data on 24,000+ emerging market companies and help them build SDG-integrated investment portfolios.

The IFC’s analyst tool “is all about scale,” Florian explains: With the click of a button, investors can unlock curated information from companies’ annual reports, news articles, and impact assessments. He notes that these documents “can be lengthy, sometimes running up to thousands of pages”. MALENA aims to extract only the relevant insights about companies’ ESG performance from these documents and summarize them in a clear and informative company dashboard.

MALENA’s sustainability impact

Investors still face a significant gap in analyzing corporate sustainability data in emerging markets. The funding gap to achieve the SDGs is about $2-3 trillion annually. But “if the $200 trillion invested annually in capital markets were redirected,” Florian points out, “significant efforts could be made to make better-informed investment decisions and identify investment opportunities relevant to the SDGs.” For example, MALENA can help investors read and structure underutilized information and evaluate companies that have previously gone uncovered.

About MALENA’s AI model

MALENA can identify more than 1200 ESG risk terms, based on which it then performs sentiment analysis to assign positive, negative or neutral sentiment to the risk terms. Florian notes that the sentiment analysis was fine-tuned to the sustainability context and unique circumstances of the local markets of the companies in question. MALENA’s risk term taxonomy covers all 17 SDGs, including all 72 underlying targets and 102 indicators. To monitor the tool’s trustworthiness, MALENA has developed a Data and Model Governance Framework, which will adapt the fundamental properties of IBM for AI ethics, encompassing model explainability, performance, trust, robustness, fairness, transparency, and drift.

Looking at the road ahead: What’s next?

The first version of MALENA was released last summer. This version was made available to a limited number of asset managers, development finance institutions, export credit agencies, and private equity funds. This summer, however, the team has been working to release a “global public good version”. The release of this version is scheduled for release in July 2023.

For more information about MALENA, have a look at their website (link) and publications (link, link).


Presenting the Global Top 100 outstanding projects: Artificial Intelligence-Based Referral System for Patients With Diabetic Retinopathy in Jalisco

Presenting the Global Top 100 outstanding projects: Artificial Intelligence-Based Referral System for Patients With Diabetic Retinopathy in Jalisco

This project provides an inspiring example of an AI-based referral system for patients with diabetic retinopathy. Aware of the high prevalence of diabetes and a shortage of ophthalmologists and eye illness detections services in the Mexican State of Jalisco, the founding members of this
project developed an AI model based on deep convolutional neural networks (DCNN) to enable a timelier detection of Diabetic Retinopathy in people’s eyes. The trained models preprocess and evaluate the suitability and quality and classify relevant ocular documentation with an exceptional specificity and sensitivity on local data.


International Research Centre
on Artificial Intelligence (IRCAI)
under the auspices of UNESCO 

Jožef Stefan Institute
Jamova cesta 39
SI-1000 Ljubljana


The designations employed and the presentation of material throughout this website do not imply the expression of any opinion whatsoever on the part of UNESCO concerning the legal status of any country, territory, city or area of its authorities, or concerning the delimitation of its frontiers or boundaries.

Design by Ana Fabjan