Machine Learning Engineer Nanodegree

Capstone Project

Project: Prediction of Stock Moving Direction

Install

This project requires Python 3.6 and the following Python libraries installed:

• NumPy
• Pandas
• matplotlib
• pyti
• brew
• scikit-learn
• imbalanced-learn
• keras

You will also need to have software installed to run and execute an iPython Notebook

We recommend installing Anaconda, a pre-packaged Python distribution that contains most of the necessary libraries and software for this project.

Code

The code is provided in the Notebooks folder. The CSV files and Clfs folder (pool of trained classifiers) are not included due to the size limitation.

Run

In a terminal or command window, navigate to the top-level project directory Notebooks/ (that contains this README) and run one of the following commands:

ipython notebook {name of notebook file}.ipynb

or

jupyter notebook {name of notebook file}.ipynb

This will open the iPython Notebook software and project file in your browser.

Data

This dataset consists of 1-min stock data from a post at Github for a time period from 06/06/2017 to 07/14/2017 (approximately 10,000 data points). A more recent dataset (from 2017-07-18 to 2017-07-21) from the same Github post (approximately 1,500 data points) was downloaded for back testing.