2021 | Foundations | Philanthropists & non-profits | Promising | SDG10 | SDG16 | SDG17 | SDG5 | SDG9 | United States
ImpactMapper Autocoding

1. General


SDG 5: Gender Equality

SDG 9: Industry, Innovation and Infrastructure

SDG 10: Reduced Inequality

SDG 16: Peace and Justice Strong Institutions

SDG 17: Partnerships to achieve the Goal


Foundations, Philanthropists & Non-Profits

2. Project Details

Company or Institution



ImpactMapper Autocoding

General description of the AI solution

By 2030, researchers predict at least $12 trillion will be dedicated to achieving the SDGs and social impact around the world. But what is actually happening with all of this capital? Too often we do not know. That means that foundations, nonprofits, and impact investors often are unclear if they are funding the right changemakers and solutions.
When aiming to track impact, most software and analytic tools focus primarily on the numbers and not the experiences and stories of people affected by the change. At the same time, organizations are sitting on treasure troves of text and report data that contain detailed information on the social change process and impact trends, but they are left unanalyzed. At ImpactMapper, we specialize in helping groups get the most out of their text data, and align that data with other quantitative impact metrics, and financial data. Our all-in-one software helps donors, nonprofits, corporates and impact investors measure and visualize social impact and sustainability.
ImpactMapper has developed a SaaS tool that allows users to manually code and tag their text data, align it with their indicators and metrics for change, like the SDGs, and visualize that data alongside quantitative data so they have a holistic view of their program impact. We are now working on AI solutions to make this manual coding process much faster through NLP and automated impact tagging suggestions for more efficient coding of text data. We are the only impact tracking tool on the market that fully allows users to analyze and visualize their qualitative data and quantitative data. We help groups analyze and learn what is working and what is not to fast-forward social change and share the stories that matter most.





3. Aspects

Excellence and Scientific Quality: Please detail the improvements made by the nominee or the nominees’ team or yourself if your applying for the award, and why they have been a success.

We are experts in quantifying the seemingly unquantifiable. Our Founder and CEO, Alexandra Pittman, PhD, is a data scientist and impact evaluation expert. She has specialized in measurement of human rights and gender equality, and developed a unique methodology and leads training programs for foundations, UN agencies, and nonprofits to support learning on how to collect and code story and text data for social impact. Last year, Entrepreneur Magazine named Alexandra Pittman an innovative tech founder in sustainability tracking. The ImpactMapper software program was developed by Pittman and her team to meet the key gap in the sector of not using the vast amounts of text data available on social change and impact. She has raised foundation grants from Oak Foundation and Arcus Foundation, and received equity financing from Katapult Impact, to develop new technological features for impact tracking.
There are no other software tools on the market designed for the philanthropic sector that take seriously the use of qualitative data and report data sources for impact tracking. This includes grantee reports, evaluations, stories and interviews, along with funding and quantitative data collected. ImpactMapper occupies a unique space transforming this text into aggregate level trends so it can be tracked with other quantitative metrics. By scaling up our AI/NLP solution which leverages interactive machine learning algorithms for user-validated automated coding, we will have the opportunity to transform how text data is valued and used in this philanthropic and international development space, by making it easier to process, track and learn from. We are in the prototype phases of development (discussed below) and will look towards IP protection once in the implementation phase. Our traction in the market is compelling with the top brands that care about human rights, engaging with our software tool and impact reporting services.

Scaling of impact to SDGs: Please detail how many citizens/communities and/or researchers/businesses this has had or can have a positive impact on, including particular groups where applicable and to what extent.

Our next phase of AI development will contribute to our ability to expand our solution, enabling a more efficient coding process to align with an organization's unique impact indicators and outcomes, as well as the SDGs, increasing our contributions and impact on the ecosystem. We will impact the philanthropic and international development ecosystem by promoting the use of text and outcomes based data that is being collected and allowing for evidence-based assessment of SDG achievements and other outcomes. At a global level, the value add will allow us to mine data on social impact that we have not seen before and see aggregate trends around lessons learned, strategies that are working and those that have not to fast-forward the social change process. In this way, we can build and enrich the evidence around SDGs with meaningful data from around the world and nuance the collective conversation around goal attainment.
We also run impact data collection projects, which have a global reach, including connecting with NGOs and partners in UNESCO member states. For example, we are currently collecting data for a project documenting the decade- long achievements of women's rights organizations around the globe, and aligning their outcomes with the SDGs. We currently have data from over 30 countries, and this collective searchable database is available for the public and development community to learn from, to see issues and populations being addressed, strategies that are working, and to connect with groups that may be working in similar spaces. See https://www.impactmapper.com/sdg5-projects/main​​ We plan to launch a similar project in the climate justice space.

Scaling of AI solution: Please detail what proof of concept or implementations can you show now in terms of its efficacy and how the solution can be scaled to provide a global impact ad how realistic that scaling is.

We have developed a proof of concept for the automated report coding prototype with the following features:
Ability to import different data sources from csv or API sources.
Using NLP, extract the names of the entities (e.g., organizations, UN, corporates) in the text.
Using NLP, search and document different pieces of text based on and assess the sentiment of the text and categorize it as positive or negative.
Exploring two different NLP algorithms to autocode text data to the SDGs, one from UN and one from Microsoft researchers. We are testing them to see which is best and technical adjustments we need to make.
Created a manual editing tool to change an automated categorization based on issue or sentiment for increased tagging accuracy.

Ultimately to build scalable algorithms, we need significant and diverse sets of data to train our algorithms. To scale up our impact in the field, we require a diverse set of philanthropic and multilateral data partnerships and support. We are working on both of these levels. To scale up on the technical side, we are building a data sharing network of UN agencies and foundations that will be sharing their grantmaking applications and/or reports to train our algorithms and develop a scalable solution for social impact tracking. In 2020, we established a data sharing partnership with UN Women and UNINFO, where they are sharing internal country level data with us for our AI projects. We are also launching a joint hackathon with UN Women in Q3 this year. We would love to collaborate with UNESCO and member states as relevant as well. We are also building a foundation consortium, and have initial interest from Malala Fund, Arcus Foundation, and others to support this initiative. We also have discussed with Candid sharing data between our APIs.

Ethical aspect: Please detail the way the solution addresses any of the main ethical aspects, including trustworthiness, bias, gender issues, etc.

At ImpactMapper, all of our work is based on the principles of human rights, gender equality, and social justice. We help donors, nonprofits, multilaterals and businesses track and increase their impact around the world. Our AI-powered features are designed to make their work more efficient and visible, so they can leverage the social changes they fight for. Our philosophy at ImpactMapper is to not use black box algorithms for categorizations without human intervention, but rather to allow for the human and expert validation of data. That is why we are building interactive machine learning algorithms for coding outcomes and impact, where a human validates or invalidates tagged outcomes data. This way you have the opportunity to train away potentially biased data and improve reliability with a human rights lens given this population are our users. This is the type of interactive learning algorithm that we are prototyping now at ImpactMapper for tagging grants and grantee report data faster. We are expanding and building a news data site to track corporate performance on human rights to make that more transparent. Our platform complies with GDPR standards and we take privacy and data ownership seriously. Any collective data that we share externally, is consent based.


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