Data Science: Capstone Part 1: Pitch + Problem Statement

Overview

In the field of data science, good projects are practical. Your capstone project should be manageable and affect a real world audience. This might be a domain you are familiar with, a particular interest you have, something that affects a community you are involved in, or an area that relates to a field you wish to work in.

One of the best ways to test ideas quickly is to share them with others. A good data scientist has to be comfortable discussing ideas and presenting to audiences. That’s why for Part 1 of your Capstone project, you’ll be preparing a lightning talk on some potential interest areas and datasets.

This deliverable will provide you with guidance to help you select an awesome topic and begin to build a polished Capstone project.

Goal: Host a lightning talk presentation describing at least two project proposals, including associated data, goals, audiences, and metrics.

REQUIRED

1. Prepare a slide deck and host a 3-4 minute lightning talk on at least two potential topics for your capstone project. For each topic, define all required areas:

2. Topic 1
   • Problem Statement
   • Potential Audience
   • Goals
   • Success Metrics
   • Data Source(s) (subject to change)
3. Topic 2
   • Problem Statement
   • Potential Audience
   • Goals
   • Success Metrics
   • Data Source(s) (subject to change)

BONUS

1. Beyond the two required topics, what other potential topics might you explore? (e.g. 3 or more)
2. For all datasets, identify their source, format, and necessary action items to obtain or access them.
3. Create a blog post of at least 500 words (and 1-2 graphics!) that describes your project idea, data, and audience. Link to it in your presentation appendix.

Remember, if you can’t find data to support your topic, then you can’t move forward.

Deliverable Format & Submission

• Slide Deck & Presentation

Suggested Ways to Get Started

Begin by Asking:

• What is the scope of the need or problem I wish to investigate?
• Who is this for? Who is impacted or affected by this data? Who would benefit from this model?
• What are my goals for this investigation?
• What does success look like? How will I know if my model performs well?
• Where will I find data for this project? Is the data available?

For the Bonus, Ask:

• What format is the data in? What specific steps do I need to take to access it?
• How will I explain this project to outside audiences?

Other Tips:

• For your 1st potential topic, start with an idea, then look for potential data that could be used to support that idea.
• For your 2nd potential topic, reverse the process; look for interesting data and then extrapolate problems it could solve and audiences it could impact.

Useful Resources

• How to give a good lightning talk.

Some ideas for Data Sources

• Google Datasets Search Tool
• Awesome Data
• Kaggle Datasets (Generally, don’t use only this if many folks have used the dataset.)
• Open Data Library
• Pandas Data Reader
• Jeff’s List of Python API Wrappers

Project Feedback + Evaluation

You will be evaluated on the requirements above using the below rubric.

RUBRIC

| Score | Interpretation | | — | — | | 0 | Project fails to meet the minimum requirements for this item. | | 1 | Project meets the minimum requirements for this item, but falls significantly short of portfolio-ready expectations. | | 2 | Project exceeds the minimum requirements for this item, but falls short of portfolio-ready expectations. | | 3 | Project meets or exceeds portfolio-ready expectations; demonstrates a thorough understanding of every outlined consideration. |

Attached here is a complete rubric for this project.