Joe Jevnik – A Worked Example of Using Neural Networks for Time Series Prediction
PyData New York City 2017
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.