PyData November Presentation Night
Details
Hello PyDataneers,
Let's meet a week before Thanksgiving to mingle and feast our minds upon using neural networks for time series prediction.
Our honored guest will be Joe Jevnik.
Schedule:
18:00 - 18:30 Gathering and mingling
18:35 - 20:00 Presentation, Q&A, some more mingling
A Worked Example of Using Neural Networks for Time Series Prediction
Joe Jevnik
Most neural network examples and tutorials use fake data or present poorly performing models. In this talk, we will walk through the process of implementing a real model, starting from the beginning with data collection and cleaning. We will cover topics like feature selection, window normalization, and feature scaling. We will also present development tips for testing and deploying models.
About the speaker:
Joe Jevnik works at Quantopian where he works on integrating data from various sources into the platform. Joe works on Zipline, Quantopian's open source backtester. He also works on the Blaze ecosystem, mainly on blaze core, odo, and datashape.
