case-study

More accurately forecast future waste volume collected across Sanergy’s FLT network.

During the high-energy, three-day marathon-style DataDive® event that took place March 4-7, 2021, volunteers on this project set out to do the following:

Build a predictive model using John Jay’s data to identify students who are at risk of dropping out, to aid John Jay’s efforts to provide better and more timely support to these students and reduce dropout rates.

Help DC Child and Family Services Agency (CFSA) caseworkers determine their clients’ eligibility for multiple programs and social services at once. 
Create a protoype of a tool and codebase that can easily be repurposed and replicated by other agencies facing similar challenges.

Develop a “proof of concept” water demand forecasting model using flow data at the microzone level for potential future scaling to other retailers in the California Data Collaborative, a unique water manager-led public private partnership that brings together utilities across the state to leverage data to help water managers ensure reliability.  

Analyze the impact of different factors VOTO Mobile can control to increase mobile survey response rates among rural women in developing countries
Develop a tool to enable VOTO Mobile to forecast response rates and design surveys to access the hardest to reach and the least represented populations in the world

Use historical customer payment behavior data to predict which new applicants are likely to be a good fit for their pay-as-you-go solar power systems program

Analyze 15 years of data to uncover predictors for the best engagements between pro bono consultants, nonprofits, and Taproot Foundation
Understand what makes a nonprofit or pro bono consultant a good fit for Taproot’s long-standing and new program delivering pro bono services to nonprofits.

Begin to understand and define “college readiness” for students enrolled at KIPP LA elementary and middle schools
Determine what factors, if any, can predict a KIPP LA student’s level of college readiness, given the available data

Prepare and anonymize never-before-released American Red Cross domestic disaster data and open data to gain insights
Explore the data descriptively with statistics and visually with maps and graphics to understand data quality and identify patterns
Prototype a model that predicts and maps which counties American Red Cross should target for its next smoke alarm installation campaigns