Data Science: Capstone Part 5: Presentation + Non-Technical Summary

Overview

Whether during an interview or as part of a job, you will frequently have to present your findings to business partners and other interested parties - many of whom won’t know anything about data science!

That’s why for Part 5, you’ll create a 15 minute presentation that delivers the most important insights from your project to an audience. You’ve already done the analytical work; now it’s time to explain your findings to the public.

Take your findings and share the most important insights from your project. Be prepared to translate things for both non-technical and technical people. Tell us the most interesting story about your data. Break down your process for a novice audience. Make sure to include compelling visuals. Time is short, so be sure to practice - and include only the most relevant components of your project.

Finally, be prepared to answer questions and explain your choices to an inquisitive audience!

Goal: A public presentation of your project, including an explanation of your model and findings for a non-technical audience.

REQUIRED

1. Host a 15-minute well-rehearsed presentation of your project for your audience.
   • Define technical terms and any basic data science concepts that inform your approach.
   • Don’t just deliver the information; tell a story about the problem and solution.
2. Prepare polished visuals and a publicly-suitable slide deck to guide your presentation.
   • Include graphs and/or visualizations.
3. Make sure you cover the following areas:
   • Goals
   • Success Criteria / Metrics
   • Data
   • Overall Approach
   • Basic description of model
   • Findings
   • Risks/Limitations
   • Impact, next steps, conclusions
4. Successfully answer questions about your project from, and for, your audience.

BONUS

1. Discuss longer term potential of your project and model.
   • Describe how you could validate your model’s performance over time
   • Explain how you would deploy your model in a production environment
2. Create a publicly hosted interactive visualization that your audience can use to further access and explore your data and findings.
   • Bonus points for embedding this into your blog post tutorial!

Deliverable Format & Submission

• Format: Public presentation of 13-17 minutes, plus 5 minutes of questions. Presentation should include interactive graphics, website, and/or slide deck.

Suggested Ways to Get Started

• Review the information you provided in the “Exective Summary” from Part 4. This is the same information you should cover here.
• The difference is that you should not assume that your audience knows anything about your problem, model, or basic data science. Structure your presentation as if explaining your model to a non-data science friend.
• Practice! Test your presentation on other GA students or friends and see where they have questions.
• Include more visuals (and less text) than you think.
• Don’t just read your presentation - deliver it!

Useful Resources

• Importance of Storytelling w Data - Tableau Whitepaper

Example Projects

Below are some great capstone projects submitted by past US data science students over the years!

• Kenya Chauche, DSI-10 built a natural language generation program trained on Shakespeare’s sonnets
• Molly Baird, DSI-11 wanted to computerize the game of SET, and succeeded admirably
• Daniel Johnston, DSI-2 built several key machine learning algos from scratch in python, comparing their performance to the scikit-learn implementations.
• Alex Schultz, DSI-3 predicts spot coffee (commodity coffee bean) price changes from sentiment analysis of an industry trade publication.
• Brice Walker, DSI-3 wanted to play with his Jetson GPU and built voice transcription from scratch.
• Caitlin Streamer, DSI-4 worked on a Kaggle dataset to predict pneumonia from chest X-rays.
• Brian Osgood, DSI-04 built a bot that crawls twitter and identifies whether an image tagged ‘lamborghini’ is actually a lamborghini.
• Frank Turner, DSI-04 uses image recognition to identify the colors used in a fashion season’s palette.
• DSI-06, team This is actually the DSI-6 group project. It’s here because it’s really, really impressive.
• Amy Taylor, DSI-06 wanted to quantify the difference between types of dance music.
• Veronica Giannotta, DSI-06 delved into the dark side of the internet and evaluated the emotional sentiment of social media content that goes viral.
• Derek Steffan, DSI-07 automates the process of creating twitch highlight reels using sentiment analysis, markov chains, and Bayesian analysis.
• Sebastian Alvis, League of Legends Not a GA Capstone, but a very compelling case for applying data science to your interests to come up with a good capstone.

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.