Final project description

The final project is a group project that shows your ability to apply the concepts and techniques learned in the course to a real-world dataset and urban application.

Project types

There are many potential products for the final project:

  1. A comprehensive assignment based on using large urban datasets for a specific application chosen from the topics discussed in the course.
  2. Creating a web-based decision-making platform using urban data.
  3. Participation in an Urban Data Challenge or collaboration with city halls, companies, agencies, or government teams.

Project report

In each case, the final project must include:

  1. A final report (no more than 10 pages, PDF is fine).
  2. A final presentation by the team in the last week.

Project description

The project will be a combination of large-scale data analysis and urban application. The project will involve the following steps:

  1. Literature review: Review the literature on the topic of the project. This should include at least 5 papers from the literature. The literature review should be included in the final report.

  2. Data collection: Collect needed data from a large urban dataset. This could be from a city, a company, or a research project.

  3. Data analysis: Analyze the data using the techniques learned in the course. This could involve mathematical modeling, network analysis, spatial analysis, machine learning, causal analysis, individual/collective models or other techniques. The project at least should involve two of the techniques learned in the course.

  4. Urban application: Apply the analysis to a real-world urban problem. This could be a policy recommendation, a new tool for urban planners, a new visualization, or other application.

  5. Topics The project should be related to one of the topics discussed in the course. This could include urban mobility, urban economics, urban health, urban planning, urban social networks, or other topics. Consult with the instructors if you are unsure if your project fits the course. Topics should be chosen by April 9th.

  6. Teamwork: The project should be done in teams of at most 2 students. Each team should have a team leader who is responsible for coordinating the project.

  7. Final report: The report should be written in a clear and professional manner. The final report must include the following sections:

    1. Introduction to the project / Motivation.

    2. Review the relevant literature about the problem.

    3. Description of the data used.

    4. Data Analysis

    5. Results.

    6. Conclusion / Discussion

  8. Final presentation: The final presentation should be a 10-minute presentation by the team. The presentation should include a description of the data, the analysis, the application, the results and a discussion of them. The presentation should be clear and professional. Project presentations will be on the week ending April 25th.

Examples of projects

Analyzing the impact of a new transportation policy

Analyze the impact of public policies on urban mobility using mobile phone data and causal methods.

  • Identify a new transportation policy in a city and analyze the impact of the policy on urban mobility. There are many recent examples, like the congestion-toll in NY, for example (see a recent paper [1])
  • Use mobile phone data to analyze the impact of the policy on the movement of people in the city.
  • Use census data and spatial regression to investigate the impact of the policy on different groups.
  • Use causal methods to identify the impact of the policy on urban mobility.

Creating a web-based tool for urban planning

For example, to analyze the impact of new business on accessibility to health food using census data, visualization, and modeling of human mobility.

  • Use large scale data about POIs and/or mobility to define accessibility of areas and socio-demographic groups to healthy food in a city.
  • Use census data and spatial models to investigate which groups are more affected.
  • Create a web-based tool that urban planners can use to analyze accessibility to healthy food in a city.
  • References to similar tools:

Create an agent-based model to study the impact of new business openings in a city

  • Use agent-based models to simulate visits to business in a city using gravity law or Huff law.
  • Use census data to define the socio-demographic characteristics of the agents.
  • Use the model to study the impact of new business openings in a city.
  • Investigate potential policy recommendations based on the results of the model.
  • References:

Participate in Urban Data Challenge

Have a look at the different Urban Data Challenges that are available. Some might be open now, but other are already closed and you can see the results.

For example:

  • The 500 Cities Data Challenge was an initiative by the Urban Institute to design innovate solutions to address social determinants of health in cities. The challenge was open to students, researchers, and practitioners. The challenge is now closed, but you can see the results here. You can access the 500 cities data here

  • Kaggle has many urban data challenges. You can see the results of past challenges and participate in new ones. For example, it has some Getting started prediction competitions for House Prices that are good for beginners here and here

  • Takahiro Yabe organized a challenge at ACM SIGSPATIAL 2024 and it is organizing a new one for 2025. You can use the materials for the 2024 edition.

  • The city of Boston organized a data challenge with their open data some time ago. Although the challenge is not open, you can look at the different tracks and data used in the challenge for your project

References

[1]
C. Cook et al., “The Short-Run Effects of Congestion Pricing in New York City.” in Working Paper Series. National Bureau of Economic Research, Mar. 2025. doi: 10.3386/w33584.
[2]
Y. Liang, S. Gao, Y. Cai, N. Z. Foutz, and L. Wu, “Calibrating the dynamic Huff model for business analysis using location big data,” Transactions in GIS, vol. 24, no. 3, pp. 681–703, 2020, doi: 10.1111/tgis.12624.