My primary research is focused on measurement and monitoring of risks in banks, both at the individual bank level and at the level of financial system as a whole. In a recent paper, we have developed a high-dimension statistical approach to measure connectivity across different players in the financial sector. We implement our model using stock return data for US banks, insurance companies and hedge funds. Some of my early research has developed analytical tools to measure banks’ default risk using option pricing models and other tools of financial economics. These projects have often a significant empirical component that uses large financial datasets and econometric tools. Of late, I have been working on several projects related to the issue of equity and inclusion in financial markets. These papers use large datasets from financial markets to understand differences in the quantity and quality of financial services received by minority borrowers. A common theme across these projects is the issue of causal inference using state-of-the art tools from econometrics. Finally, some of ongoing research projects are related to FinTech with a focus on credit scoring and online lending.
Professor Manduca’s research focuses on urban and regional economic development, asking why some cities and regions prosper while others decline, how federal policy influences urban fortunes, and how neighborhood social and economic conditions shape life outcomes. He studies these topics using computer simulations, spatial clustering methods, network analysis, and data visualization.
In other work he explores the consequences of rising income inequality for various aspects of life in the United States, using descriptive methods and simulations applied to Census microdata. This research has shown how rising inequality has lead directly to lower rates of upward mobility and increases in the racial income gap.
Screenshot from “Where Are The Jobs?” visualization mapping every job in the United States based on the unemployment insurance records from the Census LODES data. http://robertmanduca.com/projects/jobs.html
Societal control tends to be implemented from the top-down, whether that is a private corporation or a communist state. How can data science empower from the bottom-up? Computational technologies can be designed to replace extractive economies with generative cycles. My research includes AI for the artisanal economy; computational modeling of Indigenous practices; and other means for putting the power of data science in the service of generative justice.
Student moving from her knowledge of braiding algorithms, to her program for braiding patterns, to a mannequin head for installation in adult braider’s shops. https://csdt.org/culture/cornrowcurves/index.html
Greg’s research primarily investigates information flow in financial markets and the actions of agents in those markets – both consumers and producers of that information. His approach draws on theory from the social sciences (economics, psychology and sociology) combined with large data sets from diverse sources and a variety of data science approaches. Most projects combine data from across multiple sources, including commercial data bases, experimentally created data and extracting data from sources designed for other uses (commercial media, web scrapping, cellphone data etc.). In addition to a wide range of econometric and statistical methods, his work has included applying machine learning , textual analysis, mining social media, processes for missing data and combining mixed media.
My research explores the interplay between corporate decisions and employee actions. I currently use anonymized mobile device data to observe individual behaviors, and employ both unsupervised and supervised machine learning techniques.
My data science-related work deals with predicting productivity of entry-level workers using applicants’ psychometric profiles. The work has relevance for the design of AI-based hiring, job search for unemployed workers, sectoral transitions (particularly for entry-level workers), and the design of optimal incentive contracts based on worker type.
Transportation is the backbone of the urban mobility system and is one of the greatest sources of environmental emissions and pollutions. Making urban transportation efficient, equitable and sustainable is the main focus of my research. My students and I analyze small scale survey data as well as large scale spatiotemporal data to identify travel behavior trends and patterns at a disaggregate level using econometric methods, which we then scale up to the population level through predictive and statistical modeling. We also design our own data collection methods and instruments, be it a network of smart devices or stated preference experiments. Our expertise lies in identifying latent constructs that influence decisions and choices, which in turn dictate demands on the systems and subsystems. We use our expertise to design incentives and policy suggestions that can help promote sustainable and equitable multimodal transportation systems. Our team also uses data analytics, particularly classification and pattern recognition algorithms, to analyze crash context data and develop safety-critical scenarios for automated and connected vehicle (CAV) deployment. We have developed an online game based on such scenarios to promote safe shared mobility among teenagers and young adults and plan to expand research in that area. We are also currently expanding our research to explore the use of NN in context information synthesis.
This is a project where we used classification and Bayesian models to identify scenarios that are risky for pedestrians and bicyclists. We then developed an online game based on those scenarios for middle schoolers so that they are better prepared for shared road conflicts.
My research is at the intersection of Science of Science + Sociology of Organizations + Computational Social Science. I study how social and organizational factors affect scientific discovery. I am especially interested in evaluation practices in science, and whether they promote or stifle innovation. My approach relies primarily on field experiments — interventions in scientific competitions and other settings — and applying computational tools to large-scale observational data.
Current research projects include:
1. Cumulative advantage in science: Do metrics like citation counts and impact factors proxy quality and influence, or help create them?
2. Biases in expert evaluation: Do groups of experts make decisions differently from individuals?
3. Science and the media: What research is picked up by the media, and how is it covered?
Showing how often a paper has been cited causes scientists to perceive it as of lower quality, unless that paper is among the 10% most highly cited.
Professor Hines’ research focuses on the analysis of the donative behavior of Americans, and how it affects the intergenerational and interpersonal transmission of economic well-being. To what extent do parents leave property to their children and others, and how is this behavior affected by legal institutions, taxes, social norms, and other considerations? While there are no comprehensive sources of data on wills, trusts, lifetime gifts, and other forms of property transmission, there is ample available information from legal documents that with the help of natural language processing can hopefully be coded and analyzed in a systematic way.