Final Project

Students will work in small groups to complete a semester-long group project. There are a couple of options for what your final project could involve:

  1. Write an original research paper: Articulate and answer a novel research question in international development. Your project should rely on the original analysis of non-traditional data. Your goal should be to have the first draft of a short paper that could be published or presented at an academic research venue (here is an example of a successful project from a past year). Be ambitious, be practical, and start early: you need to be able to obtain and analyze the required data within the course of a semester. This project should be done in a group of 2-4.
  2. Build something useful: Build a public-facing website or app that makes insights about big data and development more accessible to a lay audience. This could be a website that uses non-traditional data to provide analysis or outputs that are useful to people studying international development (examples include: OneHundredHomes, WorldPovertyClock, PovertyMaps.net, GeoQuery, Global Forest Watch, Global Fishing Watch, FIRMS, FloodHub). Alternatively, you could build something clearly communicates technical concepts to a non-technical audience through compelling and visual data journalism (examples include this NYT report, Earth TimeLapse, India COVID response, this primer, Our World in Data, SDG Atlas, GapMinder). Whatever you build must fill an unmet need, i.e., your contribution must be different from what is already out there.  This project should be done in a group of 3-5.

There are several deadlines prior to the final paper submission. These are designed to help you identify project ideas, form teams, and get feedback from the teaching staff.

Milestones

There are a several deliverables associated with each project. All assignments are due by midnight on the date listed.

Due dateAssignmentPoints
Feb 2Project ideasN/A
Feb 9Preliminary proposal5
Feb 23Final proposal8
March 30Midterm report12
April 27Presentation10
May 4Final paper30
  1. Final project “pie in the sky” ideas. Write down 2 different ideas for a possible final project for this class. For each idea, write ~1-2 paragraphs summarizing the idea. There is no commitment here, we just want to get your creative juices flowing. Dream big, but be practical. Please note that you should do this assignment independently. Even if you are 100% certain what you want to do for your final project, and know the people you want to work with, please come up with 2 original ideas. To receive credit for this assignment: Submit your response on bCourses and also add it as a reply to this discussion on bCourses (final project milestone #1). For extra credit, respond to one of the ideas that someone else has posted (you should do this as a separate post from the one in which you provide your own 2 ideas). This assignment will count towards your participation grade.
  2. Preliminary proposal. Submit one page describing what you are thinking about doing for your final project. This document should include (1) information about the datasets you will analyze; (2) names of your team members (if you have already identified any), and (3) how certain you are that you will do this project. Also post your paragraph submission under the bcourses discussion thread (final project milestone #2) so other students can take a look before the in-class final project mixer. This is a soft commitment, your project proposal can change up until the next deliverable is due. Everyone must submit this assignment individually, even if they have already identified final project teammates. 
  3. Final Proposal: Submit a ~3 page summary of your idea. After reading this proposal, it should be clear to the reader that your project is both interesting and feasible (on this latter point, you must succinctly describe how your methods will allow you to answer your question based on your data). Think of this summary as laying out the terms of a contract that defines what you will accomplish by the end of the semester — the contract should be sufficiently well-specified that it will be easy to ascertain whether or not you have delivered on that contract. The proposal should include
    • A title
    • Names of all group members
    • 1-sentence summary of the research question you hope to answer (this sentence should end with a question mark!) or what you plan to build
    • 1-paragraph abstract
    • A description of the data you will use
    • An overview of the methods you will use
    • A short discussion of the most relevant prior work, with appropriate citations.
    • A sketch of a key figure or exhibit (for project type 1) or a mockup/wireframe (for project type 2).
    • 1 paragraph describing division of labor/responsibilities within the group
  4. Midterm report. Submit a ~6 page report of your work so far. This report should include:
    • Title, names of group members, and 1-paragraph abstract
    • An annotated bibliography that summarizes the 5-10 most relevant related papers, websites, or applications
    • Basic analysis of each of the key datasets you will be using, including tables with summary statistics and descriptive figures
    • Drafts of key analysis figures and tables (for research papers), or mockups/wireframes of what you intend to build
    • A short plan/timeline for the remaining work that needs to be done on the project
    • A list of questions that you’d like feedback on from the teaching team
  5. Presentation. Each group will give a 10 minute presentation on their project, plus 5 minutes for Q&A. I will be ruthless about cutting you off when your time is up, so please practice in advance. There is no requirement that everyone in the group speaks during this presentation, just do what feels right!
  6. Final paper. If you are writing an original research paper, please submit an 8-10 page paper using this PNAS submission template.  If you are building a tool/website, aim for 5-7 pages that motivate the need for the tool/website and discuss potential use cases.

Data source ideas

All projects are expected to include a data analysis component. Here is list of publicly available datasets that may be useful for the project. Students are also welcome to use other data sources. If you find a useful data source, please share it with the class on bCourses discussions!

Survey data

Satellite imagery

Data products derived from satellite imagery

Web and social media data

Climate and environment data

Violence and conflict data

Machine learning benchmark datasets

  • SustainBench – Benchmarks relating to SDGs
  • WILDS – benchmarking data, including LANDSAT for poverty prediction
  • Wild-Time – Time series benchmarking data, including LANDSAT and healthcare-related tasks

Large repositories of different datasets