/cnn

Using fastai and CNNs to predict stock prices

Primary LanguageJupyter Notebook

CNNs to stock prices

Since CNNs are really good at classifying images, if we convert a time series to an image, will it be able to predict the next pattern in that series?

Detailed article here: https://towardsdatascience.com/reading-charts-with-convolutional-neural-networks-cbaabdd5f478

Getting Started

These instructions will get you a copy of the project up and running on your local machine for development and testing purposes. See deployment for notes on how to deploy the project on a live system.

Prerequisites

  • fastai: fastai bakes in SOTA deep learning techniques to facilitate experiments
  • pyts: pyts contains useful time series manipulation methods, in particular imaging techniques
  • quandl: quandl provides free, quality historical stock price data.

Installing

pip install pyts
pip install quandl

for fastai it is easier to use https://course.fast.ai/start_colab.html

Deployment

Add additional notes about how to deploy this on a live system

Authors

Neo Yi Peng

License

This project is licensed under the MIT License - see the LICENSE.md file for details