International development actors and local governments must often work around data gaps when tackling important social challenges. At the same time, extensive data sources exist publicly and behind the firewalls of private companies, such as mobile phone operators, car manufacturers, retailers, banks, digital platforms, and satellite operators. At Dalberg Data Insights, we identify the data solutions to international development challenges. We access, analyze, and integrate data from different sources to design tools and specialized analytics. We further leverage and operationalize disruptive technologies such as AI or Blockchain approaches. Using our products and solutions, local and global communities can better target, implement, and evaluate their programs and initiatives.
Dalberg Data Insights
Private and public data holders already generate a large volume of data through their day to day business. This data can be leveraged to create social and economic value. However, data holders often do not have the internal processes in place to technically and legally share insights from their data with third parties.
Our tools analyze human mobility through mobile phone calling patterns in conjunction with disease incidence reports and other epidemiological factors to accurately predict the spread of infectious diseases. Managing epidemics demands accurate and actionable information, but experience indicates the lack of timely and reliable information.
MOBILITY AND URBAN PLANNING
Our tools help municipality officials prioritize infrastructure investments and better plan public transport networks. Our analysis ranges from measuring the impact of weekly markets, road works or natural disasters on traffic, to identifying the most congested areas in need of additional infrastructure.
We use the economic, mobility, and social features of mobile phone data to build models that estimate multi-dimensional poverty indices or food security indices with a high degree of accuracy, at low cost and in real-time.
GENDER DATA GAP
We use machine learning to analyze customer behavior and identify the gender of subscribers for telecom operators. By assessing phone usage, mobility patterns, and social network indicators, we can predict with over 85% accuracy the gender of a mobile phone user.
We work with data from mobile phone operators and financial institutions to map and understand the penetration of digital financial services such as bank accounts and mobile money services.