Fraym sings the praises of hyper-local human geography in data-starved locales
Like most innovations, Fraym (Booth 967) was born out of frustration. Before Fraym, the company’s leadership, who held senior positions in government and at international organizations, faced one consistent and fundamental challenge—sourcing localized population-based data to make informed decisions.
“My quest for actionable, hyper-local data began nearly two decades ago,” said Fraym CEO Ben Leo. “While serving at the National Security Council, where I advised the U.S. President on Africa-related issues, I wanted to know what people looked like and how they acted in areas affected by conflict, health crises, or other driving forces. That type of foundational information would have been incredibly helpful for establishing and executing U.S. policies in the region. Unfortunately, it simply wasn’t possible or available in most places back then, and certainly not at scale or on the timelines we needed.”
Established in 2016, Fraym produces and maintains high-resolution human geography content, focusing on data-poor areas in Africa, Asia, and Latin America.
“We’re able to help you understand population characteristics down to 1km^2,” continued Leo, who said Fraym will showcase its data layers in its booth on the GEOINT 2019 exhibit floor as well as during in-depth demonstrations taking place Monday and Tuesday at 2 p.m. in meeting room 304A.
The demos will answer questions such as: “What are the human factors that drive situational awareness around a fixed asset?”; “How can human geography improve situational awareness around a fixed asset?”; and “How can human geography layers help identify communities vulnerable to extremist violence?”.
Concluded Leo, “We’re here to show what’s possible in the realm of human geography and how far we can go beyond the traditional approach of analyzing points, lines, and polygons.”
Headline Image: Fraym’s layers deliver insights as inputs for models and predictive analytics. This map was generated by inputting HG data into machine learning algorithms and used to predict areas with high vulnerability to certain types of conflict such as farmer-herder violence in Nigeria.