My research focus is on the development and application of machine learning tools to large scale financial and unstructured (textual) data to extract, quantify and predict risk profiles and investment grade rating of private and public companies. Example datasets include social media and financial aggregators such as Bloomberg, Pitchbook, and Privco.
Jowei Chen, PhD, is Associate Professor of Political Science in the College of Literature, Science, and the Arts at the University of Michigan, Ann Arbor. Prof. Chen holds a secondary appointment in the Center for Political Studies in the Institute for Social Research.
Prof. Chen’s research focuses on political geography and political institutions in the United States. His work on legislative districts examines how the geography of Democrat and Republican voters, as well as the political manipulation of district boundaries, affects voters’ political representation in legislatures. This work uses individual-level and precinct-level data about elections, combined with computer simulations of the district-drawing process. Other research projects analyze the political composition of the federal workforce by analyzing the campaign contributions and partisanship of bureaucratic employees, linking employee records with voter registration records and campaign finance data.
Using GIS, visual analytics, and spatiotemporal modeling, Dr. Rybarczyk examines the utility of Big Data for gaining insight into the causal mechanisms that influence travel patterns and urban dynamics. In particular, his research sets out to provide a fuller understanding of â€œwhatâ€ and â€œwhereâ€ micro-scale conditions affect human sentiment and hence wayfinding ability, movement patterns, and travel mode-choices.
Rybarczyk, G. and S. Banerjee. (2015) Visualizing active travel sentiment in an urban context, Journal of Transport and Health, 2(2): 30
Rybarczyk, G., S. Banerjee, and M. Starking-Szymanski, and R. Shaker. (2018) “Travel and us: The impact of mode share on sentiment using geosocial media data and GIS” Journal of Location-Based Services (forthcoming)
My primary project, election forensics, concerns using statistical analysis to try to determine whether election results are accurate. Election forensics methods use data about voters and votes that are as highly disaggregated as possible. Typically this means polling station (precinct) data, sometimes ballot box data. Data can comprises hundreds of thousands or millions of observations. Geographic information is used, with geographic structure being relevant. Estimation involves complex statistical models. Frontiers include: distinguishing frauds from effects of strategic behavior; estimating frauds probabilities for individual observations (e.g., polling stations); adjoining nonvoting data such as from in-person election observations.
My substantive research interest is to understand the role of geography in shaping population health. Towards this end, my methodological and data science interests are twofold. First, I seek to develop and apply spatial statistical methods to model individual- and area-level health and diseases by using survey data and government statistics. Second, in light of the advance in GIS techniques and the increasingly accessible spatial data from various sources, I am exploring new approaches to integrate traditional geo-referenced survey data with non-traditional spatial data (e.g., remote sensing data, satellite data, Google search) to reduce measurement errors in demographic health research.
Kerby Shedden has broad interests involving applied statistics, data science and computing with data. Through his work directing the data science consulting service he has worked in a wide variety of application domains including numerous areas within health science, social science, and transportation research. A current major focus is development of software tools that exploit high performance computing infrastructure for statistical analysis of health records, and sensor data from vehicles and road networks.