Skip to content

README.md

Latest commit

 

History

History
56 lines (35 loc) · 1.56 KB

README.md

File metadata and controls

56 lines (35 loc) · 1.56 KB
Raw

Quantify

This is full-stack web application that leverages a Recurrent Neural Network (LSTM model) to forecast future stock prices. While it is difficult to use simplistic ML strategies to beat the market, I created this project to learn more about applications of machine learning in finance.

Images

Forecasted Apple Returns Stock Forecasting Overview

Historical Data Only

Historical Data View

Forecasted Data Only

Forecasted Data View

Technologies Used

  • Python
  • Django
  • JavaScript
  • Vue.js
  • Keras
  • Tensorflow

Set-up

I have only developed this in WSL, so please consider this when referencing my documentation. This application may not work on Windows.

  1. Set-up backend and install dependencies.
make setup-backend
  1. Start the back-end application.
make run-backend
  1. In a separate terminal, start the front-end application.
make run-frontend

You should now be able to see the application in your computer's browser.

Acknowledgments

  1. I used this valid tickers file to ensure that the correct tickers are used.
  2. I referenced this YouTube video to implement an LSTM model with Keras/Python.
  3. I referenced this article to learn about how LSTM models work.