Sample Projects

Analyzing satellite images to serve smallholder farmers

Partners: FarmDrive, The Impact Lab, The World Bank

Infer information about what farmers are growing using daily satellite images, at a fraction of the ongoing cost of collecting this information in person, to promote financial inclusion through services like input loans or crop insurance.

Approaches include: Deep learning, computer vision, transfer learning, public playbook


Illuminating mobile money experiences in Tanzania

Partners: IDEO.org

Reveal patterns in behavior and barriers to trust through analyzing millions of financial records from a large mobile network operator (MNO), in order to inform how new user-centric approaches could be designed to increase use and adoption of mobile money among low-income populations in Tanzania.

Approaches include: Human-centered design + data science, exploratory analysis, interactive visualization, rapid prototyping

case study


Predicting public health risks from restaurant reviews

Partners: Yelp, Harvard University, City of Boston

Flag public health risks at restaurants -- and increase the number of hygiene violations discovered by 25% -- by combining Yelp reviews with open city data on past inspections.

Approaches include: Machine learning challenge, natural language processing (NLP), open data, alternative data sources

case study blog


Mapping fair trade products from source to shelf

Partners: Fair Trade USA

Visualize the flow of fair trade coffee products from the farms where they are grown to the stores where they are sold, connecting the nodes in supply chain transactions and increasing transparency for customers and auditors.

Approaches include: Interactive dashboarding, GIS analysis, Tableau


Modeling patient pathways through hospitals

Partners: Haystack Informatics

Map out the probabilistic patient journeys through hospitals based on tens of thousands of patient experiences, giving hospitals a better view into the timing of the activities in their departments and how they relate to operational efficiency.

Approaches include: Predictive modeling, activity-based costing, Spark, production web application


Smart auto-tagging of K-12 school spending

Partners: Education Resource Strategies

Build algorithms that put apples-to-apples labels on school budget line items so that districts understand how their spending stacks up and where they can improve, saving months of manual processing each year.

Approaches include: Natural language processing (NLP), machine learning challenge, Excel tooling, ranked prioritization for manual follow-up


Prioritizing outreach for higher ed advancement teams

Partners: EverTrue

Help schools fundraisers prioritize their time and outreach by building a predictive model for where the next big gifts are likely to come from.

Approaches include: Predictive modeling, supervised learning, alternative data sources

case study


Putting AI into the hands of lung cancer clinicians

Partners: Bonnie J. Addario Lung Cancer Foundation

Translate advances in machine learning research to practical software for clinical settings, building an open source application through a new kind of data challenge.

Approaches include: Data challenge, deep learning, open source software, computer vision, predictive modeling, computer-aided diagnosis

challenge home


Driving data education through custom competitions

Partners: Microsoft

Source and run dedicated, white label data science competitions as capstones for data science students to test their skills on real-world data, tackling social questions like which higher ed institutions are good investments for students.

Approaches include: Private data challenge, regression analysis, predictive modeling, data science education

challenge home