The CUSP Capstone Experience

Make an impact

Reducing Carbon and Driving Large Scale Energy Efficiency.

Predictive Modeling of Opioid Overdose Risk.

Mapping Construction + Demolition Waste Flows. 

How can you impact the cities of today and tomorrow?

NYU Tandon’s Center for Urban Science + Progress (CUSP) is proud to host its annual Capstone Program to serve its mission of finding data-driven solutions to increasingly complex urban challenges. 

Each year, graduate students in the MS in Applied Urban Science & Informatics degree partner with sponsors and CUSP faculty members to collaborate on a six-month project that seeks to address a critical urban issue or research problem. Project proposal applications for the 2022 program are now closed. Applications for 2023 will open in the fall. 

How does it work?

It all starts with a question. Do you have a research problem or data-driven project that you’d like a little help with? Do you need access to both data science skills and deep policy knowledge to find a scalable solution? CUSP accepts project proposals from sponsors such as government agencies, private companies, academic institutions, think tanks, NYU faculty members–anyone who is also on a mission to make cities more equitable, efficient, livable, and technologically advanced. If accepted into the program, sponsors are paired with a team of three to five graduate students and a CUSP faculty advisor to embark on a six-month project from early February through August. The timeline for the 2022 Capstone Program is as follows (subject to change):

November 15, 2021: Deadline for sponsors to submit project proposals. 

December 13, 2021: Accepted project list finalized; sponsors notified of accepted projects.

January 24, 2022: Deadline for sponsors to submit data to be used in projects. Catalog of all available projects is provided to students. 

February 3, 2022: Meet and greet event with project sponsors, mentors, and students. 

February 7-10, 2022: Deadline for students to submit preferences for project assignments. 

February 17, 2022: Team and sponsor pairings are announced. 

May TBD, 2022: Spring milestone updates/presentations.

August TBD, 2022: Final deliverables due; Capstone Presentation and concluding event. 

Project Details

Capstone projects approach real-world challenges through problem identification and scoping, data collection, and applying data analytics and visualization techniques. Typical deliverables include urban data analytic reports, data visualizations including interactive applications, research websites, research publications, and prescriptive policy solutions. 

The Capstone Program is the pinnacle of CUSP graduate students’ hands-on experience and is tied to required Urban Science Intensive I & II courses. Therefore, it is important that any potential sponsor is prepared to meet with their student team on a recurring basis and to provide support as needed. 

The best Capstone projects are impact-driven and include a coherent, well-defined urban problem. An effective Capstone project:

  • Ties directly to the needs of the sponsor organization’s mission;
  • Identifies a discrete, tangible, and deliverable end product that can provide actionable insight;
  • Is quantitative and can be approached using a range of data science and informatics methodologies (e.g. network analysis, predictive modeling, machine learning, spatial analytics, etc.);
  • Requires data that is available and in-hand prior to the start of a project; and
  • Includes a supportive sponsor that will engage with the students, ensure access to necessary information, and assist with connecting student teams to appropriate experts and stakeholders.

CUSP received its highest number of proposals ever for the 2022 cycle! 

Projects for the 2022 cycle vary widely, with topics ranging from using VR/AR to prepare for natural disasters, to assessing patterns of prosecution decisions, to working with wearable robots that assist persons with lower-limb disabilities, to discovering what a 100% electric commute would look like. This year’s Capstone projects also hail from across the US and around the globe, taking what we learn using NYC as our lab and applying it to other urban centers such as Dallas, TX; Athens, Greece; Milan, Italy; and Bogotá, Columbia. Thank you to all who applied!

Program Highlights

Networking Opportunities

Sponsors are able to connect with future leaders of urban science as well as CUSP faculty and researchers, while students have the chance to see what various career paths look like.

Talented CUSP Student Teams

Capstone teams are made up of bright and hard-working graduate students with a diverse set of skills and cultural backgrounds to bring unique perspectives to research questions.

Publishing Potential

Deliverables for each project may vary but CUSP encourages sponsors to use their project outcomes to support their own goals and publication efforts.

Use Data & Technology for Social Good

CUSP's mission is to help cities improve so that the people in them can lead better lives. Capstone projects help us to take actionable steps towards a wide variety of observable problems.

Led by World-Class Faculty

All Capstone projects are facilitated through CUSP's faculty members, including experts in the physical and natural sciences, computer and data science, the social sciences, and engineering.

No Cost to Sponsors

There is no cost to project sponsors. All we ask is that you provide quality data, a research question that can sustain the length of the program, and time committed to meeting with student teams.

Who is involved?

CUSP Graduate Students

Capstone teams are composed of three to five CUSP graduate students who will possess a combination of technical skills ranging from data analytics, visualization, machine learning, data mining and processing, database management, modeling, and web integration, to strong abilities in real-world urban vision, social science, and public policy. These broad skills enable teams to utilize data science techniques within the constraints of political, social, and financial considerations, as well as to address issues of data privacy, validity, and transparency. Our students’ range of personal, academic, and professional backgrounds and rapidly developing skills in urban science and informatics techniques make them uniquely suited to assess and solve the increasingly complex challenges that researchers are focused on today. 

Project Advisors

For projects with external sponsors, CUSP adjunct faculty members are assigned as Capstone advisors to facilitate communication between sponsors, student teams, and course instructors as well as provide technical guidance. Advisors hail from a range of fields, from the physical sciences and math to social sciences and policy, and are assigned to projects specifically so that expertise and interests are aligned. Advisors supervise the graduate students and check in on a weekly basis, offering advice and assistance as needed. Advisors for the 2022 cycle are listed below. 

Mona Sloane

Mona Sloane, Ph.D.

Himanshu Mistry

Daniela Hochfellner, Ph.D.

Manny Patole

Adrienne Schmoeker

Richard Vecsler

Tricia Davies

Tricia Davies

Course Assistants

Six course assistants are available to help guide students through advanced topics as they work with complex data sets and policy issues. This year’s course assistants have a broad range of subject expertise, with backgrounds in computer engineering, industrial engineering, political science, international relations, transnational security, global risk, technology management, and business analytics. Contact them for an appointment or to sign up for office hours. 

Urban Science Intensive Course Professor

Portrait of Danielle Wright

Previous Sponsors

Past Projects

CUSP is an interdisciplinary research center–and our Capstone projects follow suit. Past projects vary widely and we encourage sponsors to be creative and imaginative when submitting proposals. The examples below represent a few of the topics covered in the past, but future projects are not limited by these scopes. 

Fiber endings glowing blue

New York State’s Broadband Coverage Mapping for the Reimagine New York Commission

The Reimagine New York Commission has ratified an initiative to establish an accurate baseline of consumer broadband experience in New York State. This initiative is meant to position New York as a national leader in broadband data collection, provide information for use by any community for broadband expansion projects, and support pursuit of grant funding available from the FCC, USDA, and future state programs. Through this capstone, the CUSP team aggregated multiple datasets at various spatial levels to create a broadband coverage map for New York state. This map highlights a broadband score, meant to determine accessibility of broadband connections as well as demographic factors across the census tracts. In addition to a comparison view, through which users are able to see speed data from different sources like the FCC, Ookla, etc.


A Finance Map of NYC: Reducing Carbon and Driving Large Scale Energy Efficiency with a Public Database To Support PACE Lending

Sponsor: NYU Stern Center for Sustainable Business
CUSP Mentors: Gary Friedland, Marianna Koval, and Miles Draycott 

NYU Stern Center for Sustainable Business is supporting NYC’s commitment to limit carbon emissions under the Paris Agreement, collaborating closely with the NYC Mayor’s Office of Sustainability (MOS) and the NYC Clean Energy Efficiency Corp. (NYCEEC) to bring low-cost, long-term financing (PACE) for energy efficiency retrofits and renewable energy to buildings. To achieve NYC carbon neutrality by 2050, Invest NYC SDG, a two-year Stern CSB initiative, wants to guide priorities and outreach to building owners and lenders by creating a public database with visual interface mapping to present GHG emissions, potential penalties, and open liens of almost 40,000 buildings. The CUSP Capstone project would help Invest NYC SDG Initiative to develop an interactive map of NYC that displays CO2e emission level by building, contact details for the building owner or managing agent and a list of lien holders and the results of a series of queries — either run in advance or possibly user defined.


Predictive Modeling of Opioid Overdose Risk for Targeted Public Health Interventions

Sponsor: Machine Learning for Good Laboratory
CUSP Mentor: Daniel Neill

The opioid epidemic is one of the largest public health crises in the United States; since 1999, over 814,000 people have died from a drug overdose in the US. Rhode Island has been hit particularly hard and regularly has some of the country’s highest overdose death rates. To improve forward-looking targeting of intervention efforts they seek to utilize a prediction model of areas of the state at higher risk of an overdose outbreak. As a subset of a larger team working on this effort, we developed four models to predict overdose risk at the census block group level utilizing the following algorithms: gaussian processes, random forest, gradient boost, and graph convolutional network. The first three of these achieved the project’s baseline performance target and the graph convolutional network we believe shows promise. Our model results will be folded into the larger project and this information will then be supplied to RIDOH and community organizations to deploy targeted resources to higher-risk areas. If this method proves successful, it could serve as a model for states and municipalities across the country to identify and target interventions to reduce overdose risk.


Evaluating the Geometric Properties of 2D Urban Layouts Using a Data-Driven, Deep Learning Approach

Sponsor: AI4CE Lab

Urban planners widely use geometric properties to understand cities, but current methods of quantifying city geometry are very limited. To objectively measure, compare and evaluate urban designs, urban planners need a standard metric to quantify the geometric properties of 2D urban layouts. We use a proprietary tree-structured neural network developed by the AI4CE Lab to encode the complex geometry of urban layouts and learn an expressive representation of city geometry. Using the latent representation of urban layouts, we propose three urban planning applications. Firstly, we classified Manhattan’s urban layouts using GMM clustering algorithms and Shapley interpretations to identify eleven distinct urban layout typologies. Secondly, we derived a standard metric for describing the urban layout composition of neighborhoods using dimensionality reduction. Thirdly, we generated composite urban layouts by decoding the linearly interpolated values of two distinct latent subspaces. These proof-of-concept applications validate our hypothesis that complex city geometry can be encoded using representation learning techniques for downstream urban planning applications.

Frequently Asked Questions

For Potential Sponsors

We accept sponsor applications from all public, private sector, or academic organizations looking to address a critical urban issue or research problem. Our sponsors in the past have included city agencies across the US, international universities, and non-profits. Your organization does not need to be located in New York City or the United States, as long as you can provide regular communication with your capstone team.

New York University Community: Any NYU research center, faculty member, or researcher with a new or ongoing research project is welcome to apply!

For public agencies, a Project Agreement will be developed and executed, which describes the project purpose, scope, and expected outputs. This document will also outline data sharing protocols and any restrictions on shared data.

For project sponsors other than New York City agencies, a data sharing agreement will be needed. These documents are similar to the Project Agreements described above.

We seek project sponsors that are engaged and enthusiastic about the use of data science in improving city operations and planning. We expect project sponsors to identify a primary Point of Contact for the project who will ensure data sharing agreements are executed; will provide regular feedback on the students’ work, through periodic meetings and review of progress reports and presentations; and will be able to attend the final project presentations in August. The specific expectations and time commitment will vary by the needs of the project, but project sponsors should be able to commit 1-2 hours every two weeks to the above activities. Our student teams are very capable, and this level of engagement will help to ensure the final deliverables and output provide value for, and are of use to, the project sponsor.

Please review the Capstone Sponsor Mutual Expectations.

The CUSP Data Facility is a secure research data environment with datasets, tools, and expert staff to provide research support services to students, faculty, and city agency employees.  The CUSP Data Facility (CDF) connects all of these users to relevant datasets for urban policy research. The CDF reduces the multiple technical, legal, bureaucratic, capacity, and cost barriers to data access, so that the full research, policy, and operational benefits of data products can be realized by academic researchers and students, City analysts and managers, and other key partners in urban science.

We recognize that much of the data we manage, from streaming sensor data to agency administrative data, is sensitive and we handle it accordingly. The CUSP Data Facility’s Safe Data Environment comprises a multi-faceted approach to maintain safe data, through safe people, projects, settings, and outputs.  This approach combines technical protocols, user policies, and user-centered design in order to ensure adherence to data governance requirements.

  • Safe people: regular trainings on responsible data use and privacy & confidentiality,  combined with updated online resources on best practices in data management
  • Safe projects: standards and protocols for managing access to datasets and databases at the project level
  • Safe settings: a secure data environment with restricted data ingress and egress
  • Safe outputs: a statistical disclosure limitation prior to any export of products derived from restricted data

The Data Facility and Student Capstone Projects – CUSP students and faculty and host agencies are encouraged to perform all Capstone research within the Data Facility.  CUSP will process new project data and create project workspaces where designated team members can work with their project-specific datasets and collaborate on data analysis and visualization.  Other data facility users will not have access to the project workspace.

There is no fee associated with the Capstone projects.

Proposals can be submitted through this form. 

Capstone project group selection methods will be based on several criteria including students’ ranked preferences. Based on student interest, it is possible that an approved project may not be utilized. Demographics and competencies will also be considered in order to ensure group heterogeneity. Any potential conflicts of interest must be disclosed by project sponsors in advance. 

Project sponsors are able to provide input about what types of skills may be most useful to their project activities but will not be able to directly choose their student teams.

Please email Danielle Wright ( with any additional questions about the Capstone Program.

For Students

Students enroll in USI I for their spring semester, and USI II in the summer session. Both are required courses and must be taken consecutively. Course registration dates are announced via email. 

Students are able to submit up to 5 preferred projects after viewing the Capstone catalog and attending the Meet & Greet, but selection is not guaranteed.

Students teams are carefully selected to ensure that a variety of skills and experience are included in the working group. Requests may be made, but are not guaranteed.

Classes are scheduled for Thursdays 6pm-8:30pm, but at it’s the discretion of the instructors to set the meetings.

Students can expect to spend at least 75 hours on their research project outside of regularly scheduled class each semester.