Put AI to work
June 26-27, 2017: Training
June 27-29, 2017: Tutorials & Conference
New York, NY

Bayesian deep learning in PyMC3

Thomas Wiecki (Quantopian)
4:50pm5:30pm Wednesday, June 28, 2017
Implementing AI
Location: Gramercy East/West Level: Intermediate
Secondary topics:  Deep Learning, Financial services
Average rating: ***..
(3.67, 3 ratings)

What you'll learn

  • Learn how to bridge probabilistic programming and deep learning to advance algorithmic trading

Description

Deep learning continues to dominate other machine learning approaches (and humans) in challenging tasks such as image, handwriting, speech recognition, and even playing board and computer games. This has generated a lot of interest in the quant finance community in applying deep learning in the domain of algorithmic trading. Unfortunately, algorithmic trading poses a unique set of challenges—specifically, both the risk (i.e., uncertainty) of certain trading decisions and the fact that market behavior changes over time (i.e., nonstationarity) are not handled well by deep learning.

Thomas Wiecki demonstrates how to embed deep learning in the probabilistic programming framework PyMC3 and elegantly solve these issues. Expressing neural networks as a Bayesian model naturally instills uncertainty in its predictions.

Photo of Thomas Wiecki

Thomas Wiecki

Quantopian

Thomas Wiecki is the lead data science researcher at Quantopian, where he uses probabilistic programming and machine learning to help build the world’s first crowdsourced hedge fund. Among other open source projects, he is involved in the development of PyMC—a probabilistic programming framework written in Python. A recognized international speaker, Thomas has given talks at various conferences and meetups across the US, Europe, and Asia. He holds a PhD from Brown University.

Comments on this page are now closed.

Comments

Picture of Thomas Wiecki
Thomas Wiecki | QUANTITATIVE RESEARCHER
06/29/2017 5:56am EDT

Thanks for coming to my talk. I will upload the slides as soon as I figure out how to get the videos displayed.

In the meantime, the content is largely taken from my blog which also much more background and references: http://twiecki.github.io
Specifically:
part 1 and part 2

Check out Quantopian if you are interested in how these concepts relate to algorithmic trading.

Finally, you can follow me on twitter

Sorry for double posting, the links didn’t show up correctly before. If a moderator sees this, please delete the previous post.

Picture of Thomas Wiecki
Thomas Wiecki | QUANTITATIVE RESEARCHER
06/29/2017 5:53am EDT

Thanks for coming to my talk. I will upload the slides as soon as I figure out how to get the videos displayed.

In the meantime, the content is largely taken from my blog which also much more background and references: http://twiecki.github.io.
Specifically:
http://twiecki.github.com/blog/2016/06/01/bayesian-deep-learning/ and http://twiecki.github.com/blog/2017/03/14/random-walk-deep-net/

Check out Quantopian if you are interested in how these concepts relate to algorithmic trading: https://www.quantopian.com

Finally, you can follow me on twitter here: https://twitter.com/twiecki

Laureano Gomez | VICE PRESIDENT
06/29/2017 5:27am EDT

Great presentation. You mentioned that you will be posting the presentation on your blog. please let me know when that happens.I have lots of following up subjects, but before I would like to understand it better. Thanks, LG