Skip to content

A predictive platform for stock market prediction, utilizing shallow machine learning algorithms built from scratch such as SLR and MSLR, as well as deep learning methods such as LSTMs + RNNs built with Keras.

Notifications You must be signed in to change notification settings

roshanr11/Deep-Learning-for-Trading-RNN-LSTMs-getRichWithStocks.py

Folders and files

NameName
Last commit message
Last commit date

Latest commit

 

History

37 Commits
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 

Repository files navigation

getRichWithStocks.py

An interactive learning platform from scratch for beginners and experts alike in the trading industry as my final term project for Fundamentals of Programming [15-112] at Carnegie Mellon in under 3 weeks.

This project consists of the following main parts:

  • Indicators and graphs based on stock indicators written from scratch
  • Simple linear regression/multiple linear regression machine learning models built from scratch [shallow learning, without use of sk-learn]
  • Long short term memory model (LSTMM) deep learning RNN model built with Keras

This stock simulation game helps users enforce good trading practices and provides a rough prediction of the trend of the desired stock trained on a selected data interval.

Themes:

  • Helping users understand best practices
  • Writing technical analysis indicators as well as shallow machine learning algorithms from scratch
  • Utilizing cutting-edge deep learning models (LSTMM) to predict stock data

How to run: download the following modules using "pip install <module name>" without the < and >

Modules:
    Pandas
    Numpy
    sk-learn
    seaborn
    matplotlib
    Keras 

Ensure that all files are in the same folder. Run "modes_and_UI.py" in an editor of your choice, and enjoy! :)

About

A predictive platform for stock market prediction, utilizing shallow machine learning algorithms built from scratch such as SLR and MSLR, as well as deep learning methods such as LSTMs + RNNs built with Keras.

Topics

Resources

Stars

Watchers

Forks

Releases

No releases published

Packages

No packages published