Data for Solving
Global Challenges

World Data Lab specializes in creating economic and demographic models that help organizations make data-driven decisions. Our global team of data scientists, economists, demographers, and developers are passionate about combining new data sources with groundbreaking methods to push the frontiers of what is knowable.

Granular models of income for every country—based on peer-reviewed methodologies

Leveraging data science to support reaching Sustainable Development Goal 1

The world's first global life expectancy model and custom spatial demography models: population density + age structure

Age Modeling

Advancements in data science are rapidly creating a new field: spatial demography. Starting in 2017, we partnered with GeoVille and the European Space Agency to develop a new technique for predicting and forecasting the age structure of a population living in a given city block. By integrating earth observation (EO) data with sophisticated demographic techniques (including Bayesian Model Averaging), we have pioneered a new product called AgeSpot.

Methodology: Bayesian Model Averaging

AgeSpot computes the number of persons in a designated age bracket likely to live in a particular area. Results can be obtained up to the 50 by 50 meters building block level. AgeSpot’s methodology involves establishing a class of linear regression models. These models are then integrated into a Bayesian Model Averaging approach where we estimate the explanatory power of each linear model. The resulting estimates are then used to create a weighted average of the results of all models. To execute forecasts, we also include an Urban Growth Model which shows which areas are expected to be urban or rural in future years. The main sources of input data are satellite imagery and census information.

Read the blog

USE CASES
Putting Our Data
To Work
DESCRIPTION
CLIENT
Feasability Study We developed a highly predictive age structure model of the city of Vienna at the 50 sqm grid level. When validated against 2015 census data, the model was more than 98% accurate. This model, prepared as a feasibility study, was well-received and has subsquently been awarded a second tier of funding to test results in other cities and data environments.
use clients image
LET'S COLLABORATE
Map Your Market's
Age Patterns

We are currently interested in partnering with global companies as champions for the further roll-out and testing of AgeSpot in new cities and markets. Corporate champions provide a general use-case for the application of the AgeSpot model in addition to requirements. We then customize AgeSpot for the champion's needs and deliver a final product to inform the organization's strategy and planning efforts.