Uncategorized

To find patterns in text data to better understand the shared experiences of vulnerable families and youth

To track the lifecycle of their tutors and understand what makes for a successful pairing between tutor and student.

To help Shooting Star Chase understand their own data and use it to find the missing children

Automate a data-driven process for targeting villages to receive cash transfers.
Use satellite imagery and machine learning to identify, on a village-by-village level, the proportion of thatch and metal roofed homes, with thatch as a proxy for extreme poverty.

Look for patterns in temperature failures—specific clinics, types of refrigerators, and more—to identify which clinics could most stand to benefit from opportunities for improvement.
Help Nexleaf improve the cold chain supply to deliver more unspoiled life-saving vaccines to people in need
Get additional insight into how data analysis can be improved in the future to help Nexleaf achieve their impact

Examine counselor and teen text exchanges to help counselors more effectively serve teens in crisis.
Help counselors understand what factors could improve positive outcomes.
Recognize patterns to allow Crisis Text Line volunteers to respond faster to potentially harmful situations and interact more effectively with teens in crisis.

Predict future human rights violations based on Amnesty International’s decades of carefully tracked Urgent Action alerts.
Connect human rights supporters with information and each other to swiftly take coordinated action where they are needed most.

Create an affinity score metric that demonstrates how swayable specific elected officials—how quickly and strongly that official aligns behavior to the special interests providing funding.
Track how official positions change over time—via a bill’s language as it goes through the legislative process—to gauge the influence of special interests.
Build simple visual models that reveal the inner workings of our legislative process and its consequences.

Determine if real-time data sources can take some of the guessing out of inflation rates.
Identify price data at sub-national levels that could enhance inflation calculations.
Create a “defining chart” to further refine inflation calculations and improve monetary policy reactions.