The study of large complex systems of structured strategic interaction, such as economic, social, biological, financial, or large computer networks, provides substantial opportunities for fundamental computational and scientific contributions. My research focuses on problems emerging from the study of systems involving the interaction of a large number of “entities,” which is my way of abstractly and generally capturing individuals, institutions, corporations, biological organisms, or even the individual chemical components of which they are made (e.g., proteins and DNA). Current technology has facilitated the collection and public availability of vasts amounts of data, particularly capturing system behavior at fine levels of granularity. In my group, we study behavioral data of strategic nature at big data levels. One of our main objectives is to develop computational tools for data science, and in particular learning large-population models from such big sources of behavioral data that we can later use to study, analyze, predict and alter future system behavior at a variety of scales, and thus improve the overall efficiency of real-world complex systems (e.g., the smart grid, social and political networks, independent security and defense systems, and microfinance markets, to name a few).
I develop fast and principled methods for exploring and understanding one or more massive graphs. In addition to fast algorithmic methodologies, my research also contributes graph-theoretical ideas and models, and real-world applications in two main areas: (i) Single-graph exploration, which includes graph summarization and inference; (ii) Multiple-graph exploration, which includes summarization of time-evolving graphs, graph similarity and network alignment. My research is applied mainly to social, collaboration and web networks, as well as brain connectivity graphs.
Liza Levina and her group work on various questions arising in the statistical analysis of large and complex data, especially networks and graphs. Our current focus is on developing rigorous and computationally efficient statistical inference on realistic models for networks. Current directions include community detection problems in networks (overlapping communities, networks with additional information about the nodes and edges, estimating the number of communities), link prediction (networks with missing or noisy links, networks evolving over time), prediction with data connected by a network (e.g., the role of friendship networks in the spread of risky behaviors among teenagers), and statistical analysis of samples of networks with applications to brain imaging, especially fMRI data from studies of mental health).
Our research is concerned with evidence-based optimization, the idea of optimizing complex systems holistically, exploiting the unprecedented amount of available data. It is driven by an exciting convergence of ideas in big data, predictive analytics, and large-scale optimization (prescriptive analytics) that provide, for the first time, an opportunity to capture human dynamics, natural phenomena, and complex infrastructures in optimization models. We apply evidence-based optimization to challenging applications in environmental and social resilience, energy systems, marketing, social networks, and transportation. Key research topics include the integration of predictive (machine learning, simulation, stochastic approximation) and prescriptive analytics (optimization under uncertainty), as well as the integration of strategic, tactical, and operational models.
The video above is of a planned evacuation of 70,000 persons for a 1-100 year flood in the Hawkesbury-Nepean Region using both predictive and prescriptive analytics and large data sets for the terrain, the population, and the transportation network.
My research is broadly concerned with corporate governance and the effects of finance on society. Recent writings examine how ideas about corporate social responsibility have evolved to meet changes in the structures and geographic footprint of multinational corporations; whether “shareholder capitalism” is still a viable model for economic development; how income inequality in an economy is related to corporate size and structure; why theories about organizations do (or do not) progress; how architecture shapes social networks and innovation in organizations; why stock markets spread to some countries and not others; and whether there exist viable organizational alternatives to shareholder-owned corporations in the United States. Recent publications are available at http://webuser.bus.umich.edu/gfdavis/articles.htm.
My research interests are in the areas of statistical learning, analysis of high-dimensional data, statistical network analysis, and their applications in biology, health sciences, finance and marketing.