Problem Statement: The NYC 311 service request system represents one of the most significant links between citizens and city government, account for more than 8,000,000 requests annually. Increasingly, these data are being used to develop predictive models of citizen concerns and problem conditions within the city. However, predictive models trained on these data can suffer from biases in the propensity to complain (or make a request) that can vary based on socio-economic and demographic characteristics of an area, cultural differences that can affect citizens’ willingness to interact with their government, and differential access to internet connectivity.

Research Objectives: The goal of this project is to estimate the likelihood of citizens to utilize the 311 system across NYC’s neighborhoods.

Background/Context: Cities across the United States are implementing information communication technologies in an effort to improve government services.  One of such innovations in e-government is the creation of 311 systems, offering a centralized platform where citizens can request services, report non-emergency concerns, and obtain information about the city via hotline, mobile or web-based applications. These systems are generating massive amounts of data that, when properly managed, cleaned, and mined, can yield significant insights into the real-time condition of the city. Similarly, the use of machine learning algorithms to predict potential problems in the city is expanding, and 311 data have become a popular source of training data.

Methods: We introduce a three-step process to evaluate the propensity to complain: (1) we identify the ratio between complaints and violations, as an indicate of actual conditions in a neighborhood, (2) we predict the expected volume of a particular violations in a given area, and (3) we compare the actual number of complaints to the predicted violation volume to quantify discrepancies across the City.

Expected Results and Outputs: The novel opportunity to predict complaint volumes over time will contribute to the efficiency of the 311 system by informing short- and long-term resource allocation strategy and improving the agency’s performance in responding to requests. For instance, the outcome of our longitudinal pattern analysis allows the city to predict building safety hazards early and take action, leading to safer residential accommodations. Furthermore, findings will provide novel insight into equity and community engagement through 311, and provide the basis for acknowledging and accounting for bias in machine learning applications trained on 311 data.

Partners and Collaborators

NYC311, NYC Mayor's Office of Operations

Team Members

Boyeong Hong, Kristin Korsberg, Xinshi Zheng, Constantine Kontokosta

Funding

MacArthur Foundation

Research Team

Constantine E. Kontokosta, PhD, PE

DIRECTOR, URBAN INTELLIGENCE LAB; Assistant Professor of Urban Informatics; CUSP Deputy Director for Academics; Head, Quantified Community

Boyeong Hong

PhD Candidate

Constantine E. Kontokosta, PhD, PE

DIRECTOR, URBAN INTELLIGENCE LAB; Assistant Professor of Urban Informatics; CUSP Deputy Director for Academics; Head, Quantified Community

ckontokosta@nyu.edu

Prof. Kontokosta brings training urban planning, data science, economics, and systems engineering to the data-driven study of cities.

Professor Constantine E. Kontokosta, PhD, PE, is an Assistant Professor of Urban Informatics in the Department of Civil and Urban Engineering and the Center for Urban Science and Progress (CUSP) at New York University, is the Director of the Urban Intelligence Lab, and is the Deputy Director for Academics at CUSP. He holds a faculty appointment as Visiting Professor of Computer Science at the University of Warwick, and is affiliated faculty at the NYU Wagner School of Public Service and Marron Institute for Urban Management. He is also the Principal Investigator and Head of the CUSP Quantified Community research facility, a groundbreaking project underway at five districts in New York City – at the Hudson Yards development in New York City; in Lower Manhattan; at Governor’s Island, and in Red Hook and Brownsville, Brooklyn – that is building sensor-enabled urban neighborhoods to study the impact of the built environment on well-being and human behavior. As one of the first faculty to join CUSP, Constantine is part of the CUSP founding leadership team, setting the Center’s strategic priorities and leading the design and implementation of its academic programs in urban data science, growing from just two to over 50 faculty and staff and 100 graduate students in three years. He serves as Faculty Engineer-in-Residence at the NYU Tech Incubators, where he mentors cleantech and smart city start-up companies from early stage idea refinement to technology demonstration and deployment. He is a 2017 recipient of the NSF CAREER award for his research in urban informatics for smart, sustainable cities.

Dr. Kontokosta‘s research lies at the intersection or urban planning, data science, and systems engineering, focusing on using big data and new sensing technologies to better understand the dynamics of physical, environmental, and social systems in the urban environment. His work has been published in leading academic journals in fields including science, economics, urban policy and planning, and engineering, and has two forthcoming books, one on data-driven city operations and planning and the other on the subject of big data and urban sustainability. He collaborates with numerous city agencies in the U.S. and internationally on issues of urban sustainability and resilience policy and planning and city operations, including a multi-year effort to lead data analysis on building energy efficiency with the NYC Mayor’s Office of Sustainability. Dr. Kontokosta’s work has been featured in the Wall Street JournalNew York TimesCNN, NPR, Fast CompanyCityLab, Bloomberg NewsFinancial Times, APS Physics, and ASCE’s Civil Engineering Magazine, among other national and international media outlets.

Dr. Kontokosta holds a Ph.D., M.Phil, and M.S. in Urban Planning, specializing in urban economics and econometrics, from Columbia University, a M.S. in Real Estate Finance from New York University, and a B.S.E. in Civil Engineering Systems from the University of Pennsylvania. He has received research funding from the MacArthur Foundation, the Sloan Foundation, the National Science Foundation, Siemens Corp., CBRE Group, Inc., and the U.S. Department of Housing and Urban Development, among others. Kontokosta has won the IBM Faculty Award, Goddard Junior Faculty Fellowship, the Google IoT Research Award, and NYU’s Award for Teaching Excellence. He is also a recipient of the C. Lowell Harriss Dissertation Award, the Columbia GSAS Dissertation Award, the Charles Abrams Award for Research in Social Justice, the Best Paper Award at the Bloomberg Data for Good Exchange in 2015, and has been named a Fulbright Senior Scholar in Urban Planning.

Dr. Kontokosta is a licensed Professional Engineer, a member of the American Institute of Certified Planners, a USGBC LEED Accredited Professional, and has been elected a Fellow of the Royal Institution of Chartered Surveyors (RICS).  In addition, he has served on the NYC Mayor’s 80×50 Task Force, as Vice Chair of the Suffolk County Planning Commission, and on the Boards of the UNEP SBCI and the Royal Institution of Chartered Surveyors. He is an accomplished real estate entrepreneur, and, together with his brother, Michael Kontokosta, designed, built, and owns Kontokosta Winery, the Harborfront Inn, and Cove Place Inn, all on the North Fork of Long Island, as well as numerous properties in New York City and the East End.

Boyeong Hong

PhD Candidate

boyeong.hong@nyu.edu

My research interests focus on how to apply urban informatics to real world problems in urban planning and operations.

I hold a master degree in Applied Urban Science and Informatics from NYU Center for Urban Science and Progress (CUSP). While at CUSP, I was a Graduated Research Assistant in Identifying E-Waste (Electronic waste) generation in New York City project in addition to working on data analytics for capital planning with NYC Department of City Planning as part of my capstone project. Most recently, I have been working at the Pratt Center for Community Development translating geospatial data into problem solving insight through GIS mapping and analysis. Prior to CUSP, I have participated in various research projects related to urban planning and data analytics in Seoul, South Korea. I have a Bachelor degree in Architecture from Yonsei University and a Master of City Planning degree from Seoul National University.