Big Data for Social Good

Big data constitute a huge opportunity. Never before have researchers had the opportunity to mine such a wealth of information that promises to provide insights about the complex behavior of human societies. While the privacy implications of this data should not be understated, we aim to show that these types of massive datasets can be leveraged to better serve both the billions of people who generate the data, and ultimately the societies in which they live.

The Causal Structure of Food Shortage in Uganda


How soon in advance can we predict a food shortage? Variables such as market prices, drought, migrations, previous regional production, and seasonal variations all play a role in this classification and causal structure learning model to predict whether a rural inhabitant is likely to encounter difficulty in obtaining food. - G. Okori, J. Quinn

A Causal Model for Quality of Schooling

A key challenge for policymakers in many developing countries is to decide which intervention or collection of interventions works best to improve learning outcomes in their schools. Our aim is to develop a causal model that explains student learning outcomes in terms of observable characteristics as well as conditions and processes difficult to observe directly. - N. McGinn, M. Moussavi

Generative Models of the Nairobi Slums

Over one billion people - or nearly one in every three urban residents - live in informal settlements and slums. Coupling mobile phone data with mathematical models and statistical inference, we hope to better understand the dynamics of these establishments and ultimately develop predictive models to better serve this underrepresented population. - A. Wesolowski, N. Eagle

Computational Transport Planning and Modeling in Kigali

Kigali's cities planners are inundated with data about how urban infrastructure in Rwanda's capital is being utilized. Generative models are needed to better inform decisions ranging from broad transport planning questions to the minutia such as the optimal placement of the next public latrines. - A. Vaccari, N. Eagle

Modeling the Dynamics of Urbanization on Social Support Networks

What is attracting migrants to urban areas within the developing world? Using 4 years of movement and communication data, it is possible to model the reinforcing social mechanisms that could explain their recent rapid growth. - L. Bettencourt, Y. de Montjoye, N. Eagle

Expectation-Maximization for Mobile Crowdsourcing

There are over one billion mobile phone subscribers who live on less than 5 dollars a day. Using techniques such as Expectation-Maximization, we are developing a system that enables people to earn small amounts of money by completing simple tasks on their phones. - N. Eagle, B. Olding

Is Crime a Contagion?

Can we quantify a crime wave? Is crime contagious? Given the time, place, and nature of a crime, we are attempting to infer casual relationships between crimes and locations across a city. - J. Toole, J. Plotkin, N. Eagle

Quantifying the Stability of Society

Is there such a thing as a 'poverty trap'? Logistic classifiers applied on communication and census data point to a new mechanism for poverty that relates to the persistence of relationships. This analysis shows that economic exchanges flow primarily through these persistent edges and the inability to maintain these ties can prevent upward economic mobility. - Y. de Montjoye, A. Clauset, N. Eagle

Economic Shocks in Rwanda

Do people react to economic shocks in a similar manner? Time-series analysis of anonymized mobile phone records coupled with random surveys, will hopefully lead to better insight about the dynamics of rural economies. - J. Blumenstock, N. Eagle

Communication as a Lens into Poverty

How do communication patterns reflect poverty? We find the principal components of a wide range of diversity metrics, including Shannon entropy, explain over two-thirds the variance of regional socioeconomic status. - N. Eagle, M. Macy, R. Claxton