Data Collaborative Case Study: Leveraging Telecom Data to Aid Humanitarian Efforts

By Michelle Winowatan, Andrew J. Zahuranec, Andrew Young, and Stefaan Verhulst

This is the fourth installment of an ongoing series of case studies on Data Collaboratives and Data Stewardship. These case studies intend to provide insights toward leveraging private data for public good in a systematic, sustainable and responsible manner. Subscribe to our Data Stewards Newsletter to be notified of future releases.

Photo by Michael YL Tan on Shutterstock

Summary: Following the 2015 earthquake in Nepal, Flowminder, a data analytics nonprofit, and NCell, a mobile operator in Nepal, formed a data collaborative. Using call detail records (CDR, a type of mobile operator data) provided by NCell, Flowminder estimated the number of people displaced by the earthquake and their location. The result of the analysis was provided to various humanitarian agencies responding to the crisis in Nepal to make humanitarian aid delivery more efficient and targeted.

Data Collaboratives Model: Based on our typology of data collaborative practice areas, the initiative follows the trusted intermediary model of data collaboration, specifically a third-party analytics approach. Third-party analytics projects involve trusted intermediaries — such as Flowminder — who access private-sector data, conduct targeted analysis, and share insights with public or civil sector partners without sharing the underlying data. This approach enables public interest uses of private-sector data while retaining strict access control. It brings outside data expertise that would likely not be available otherwise using direct bilateral collaboration between data holders and users.

Data Stewardship Approach: The data stewards involved in this project exercised the five functions at different points in the collaboration. NCell and Flowminder demonstrated the first function of data stewards when they set up a collaboration in advance of the earthquake. This enabled their teams to exercise the second function: coordinating parties involved in the collaborative response. The third function — data audit and assessment of value and risk — was built into their data sharing mechanism. Flowminder performed the fourth function by disseminating the findings. Finally, the two organizations are still maintaining their collaboration well beyond the 2015 earthquake, demonstrating the fifth function of data stewards.

Operational variables for “Using Telecom Data to Aid Humanitarian Efforts after the 2015 Earthquake in Nepal” data collaborative. Detailed description of each variable can be found here.

Read the full case study here.




Responsible Data Leadership to Address the Challenges of the 21st Century

Recommended from Medium

Info for your AI

Estimate sample size for Confidence Intervals and Hypothesis Testing

An Exploratory Data Analysis Of Netflix Content with Python

The 100 Page Machine Learning Book

What is a data dictionary?

The Fallacy of Big Data: Data Science and the Theory of “Jobs to Be Done”

Data Preprocessing Using Sklearn

Day 52: 60 days of Data Science and Machine Learning Series

Get the Medium app

A button that says 'Download on the App Store', and if clicked it will lead you to the iOS App store
A button that says 'Get it on, Google Play', and if clicked it will lead you to the Google Play store
Michelle Winowatan

Michelle Winowatan

More from Medium

Integrating Privacy Compliance and Privacy by Design

Why Classical Persona segmentation is useless for operational Marketing

Organising for customer centricity & scale

Decision Points on Comment Form (with Schema Details) Mapped for 10 of the S1000D Issues: 1.9