Skip to content
/ SharkStock Public

Automate swing trading using deep reinforcement learning. The deep deterministic policy gradient-based neural network model trains to choose an action to sell, buy, or hold the stocks to maximize the gain in asset value. The paper also acknowledges the need for a system that predicts the trend in stock value to work along with the reinforcement …

69 stars 32 forks Branches Tags Activity
Star
Notifications You must be signed in to change notification settings

BangaloreSharks/SharkStock

BranchesTags

Folders and files

NameName
Last commit message
Last commit date

Latest commit

 

History

29 Commits
BOT5
BOT5
 
 
BOT_1
BOT_1
 
 
BOT_2
BOT_2
 
 
BOT_3
BOT_3
 
 
BOT_4
BOT_4
 
 
archives
archives
 
 
inputshark
inputshark
 
 
pickles
pickles
 
 
sairen
sairen
 
 
training
training
 
 
.gitignore
.gitignore
 
 
BOT_4_actor.h5
BOT_4_actor.h5
 
 
BOT_4_critic.h5
BOT_4_critic.h5
 
 
README.md
README.md
 
 
bot4_test.py
bot4_test.py
 
 
checkpoint
checkpoint
 
 
ddpg_test_weights_actor.h5f
ddpg_test_weights_actor.h5f
 
 
ddpg_test_weights_critic.h5f
ddpg_test_weights_critic.h5f
 
 
firstderivtest.py
firstderivtest.py
 
 
my-model.data-00000-of-00001
my-model.data-00000-of-00001
 
 
my-model.index
my-model.index
 
 
my-model.meta
my-model.meta
 
 
requirements.py
requirements.py
 
 
script_currnews.py
script_currnews.py
 
 
script_currstock.py
script_currstock.py
 
 
secwiki_tickers.csv
secwiki_tickers.csv
 
 
sentiment_currnews_dataformat.py
sentiment_currnews_dataformat.py
 
 
test.py
test.py
 
 
test_sentimental.py
test_sentimental.py
 
 

Repository files navigation

# SharkStock

SharkStock is a automated stock trading bot that uses reinforcement learning. The project is under development.

Collborators:

  • Anvitha G K Bhat
  • Akhil Raj Azhikodan

Intallation Guide

  • Create virtual environment
virtualenv senv
source senv/bin/activate
  • Install dependencies
pip install -r requirements.txt

About

Automate swing trading using deep reinforcement learning. The deep deterministic policy gradient-based neural network model trains to choose an action to sell, buy, or hold the stocks to maximize the gain in asset value. The paper also acknowledges the need for a system that predicts the trend in stock value to work along with the reinforcement …

Topics

trading-bot deep-reinforcement-learning recurrent-neural-networks stock-market policy-gradient convolutional-neural-networks sentiment-classification

Resources

Readme
Activity
Custom properties

Stars

69 stars

Watchers

17 watching

Forks

32 forks
Report repository

Releases

No releases published

Packages

No packages published

Contributors 2

  •  
  •  

Languages