Chris Conlan

Financial Data Scientist

  • About
  • Blog
    • Business Management
    • Programming with Python
    • Programming with R
    • Automated Trading
    • 3D Technology and Virtual Reality
  • Books
    • The Financial Data Playbook
    • Fast Python
    • Algorithmic Trading with Python
    • The Blender Python API
    • Automated Trading with R
  • Snippets

Stepping Into Data Science (Presentation & Photo Gallery)

April 22, 2017 By Chris Conlan Leave a Comment

We had great success last week presenting our new software for multivariate data visualization. I’d like to thank James Wang, Gretchen Martinet, and Jeff Holt of University of Virginia for making this presentation possible.

Background

James and I have a history of linking up to prototype cool tech products. We have very complimentary skill sets when it comes to computers. (The union of our skills hits every category listed here: Programming Options for Rapid Prototyping.)

Location

Nau 101 is UVA’s biggest lecture hall. We were honored to share the hall that evening with some of the country’s best political thinkers and comedians. It’s a really well-built, acoustically balanced, and modern venue.

Opener

For this presentation, we created a scalable, VR-enabled, multivariate data visualization platform. We called the event Stepping Into Data Science because virtual reality quite literally allows you to step into your data.

A photo of my own workstation at the University of Virginia

Thesis

The value of a data science education is increased primarily via learning the tools of the trade (the models) and secondarily by the ability to featurize data. Featurization is the art of pruning, transforming, and formatting data in a way that is easy for models to understand. Without advanced visualization capabilities, featurization is difficult and imprecise on high-dimensional data. Data scientists must have an intuitive understanding of the data to be able to featurize it effectively. This is where VR comes in.

Demonstration

We take the reader through a few examples that help us wrap our heads around the classic Fischer’s Iris data, much in the same way I do here: Visualizing N-Dimensional Data.

Implementation

Scalability, as promised, is achieved through the following network configuration.

“Whoooooaaaaaaaaa”

It looks really cool when actually strap into the headset. I spent the whole presentation going on about intuition and wrapping your head the data, none of which you can actually do until you put on the headset and explore with the remote. Special thanks to James for helping everyone out with this.

Thanks to Our Team

Thanks again to James Wang, Professor Gretchen Martinet, and Professor Jeff Holt for supporting the presentation. Thanks to the UVA Department of Statistics for sponsoring the presentation.

James Wang (left), Chris Conlan (center), Prof. Gretchen Martinet (Right)
From the right, Prof. Gretchen Marinet, Prof. Jeff Holt, Prof. Holt’s students
Thanks to our great audience for the enthusiasm and thoughtful questions. Pictured is myself answering a tough one.

Filed Under: 3D Technology and Virtual Reality, Chris Conlan Blog

Leave a Reply Cancel reply

Latest Release: The Financial Data Playbook

The Financial Data Playbook

Available for purchase at Amazon.com.

Algorithmic Trading

Pulling All Sorts of Financial Data in Python [Updated for 2021]

Calculating Triple Barrier Labels from Advances in Financial Machine Learning

Calculating Financial Performance Metrics in Pandas

Topics

  • 3D Technology and Virtual Reality (8)
  • Automated Trading (9)
  • Business Management (9)
  • Chris Conlan Blog (5)
  • Computer Vision (2)
  • Programming with Python (16)
  • Programming with R (6)
  • Snippets (8)
  • Email
  • LinkedIn
  • RSS
  • YouTube

Copyright © 2022 · Enterprise Pro Theme On Log in