Overview

What is this Project?

Stock Trading Bot using Reinforced Learning on S&P500 dataset to predict the future stock prices. The implimentation uses Q-learning Algorithm to achieve the goal state.

Click here for the complete Documentation .

Features

• [x] Reinforcement Learning
• [x] Deep Q-learning Algorithm
• [x] Supports different datasets
• [x] And More...

Contents

• Usage
• Requirements
• Contribute
• Tech Stacks
• License
• Author

Usage

1. Getting the Project

• Clone the repository (git clone https://github.com/shaurya-src/Reinforced-Stock-Trading.git)
• Install all the dependencies/requirements.
• Setup the project in an editor (ex. PyCharm)

2. Train the model

Open terminal in the directory of cloned project.

python train.py stock_dataset 10 100

The format is: python training_script.py training dataset Window Size # of episodes

• Window size and no. of training episodes can be changed for increasing accuracy.

3. Evaluate the model

Finally, for eavluation of the model:

python evaluate.py test_dataset model_ep100

The format is: python evaluation_script.py test dataset model_no.

• Change the model no. to check different models, models are set to save after every 10 episodes.

Requirements

• Python 3.x
• Keras
• NumPy

Contribute

Any contributions you make are greatly appreciated.

1. Fork the Project
2. Create your Feature Branch (git checkout -b feature/NewFeature)
3. Commit your Changes (git commit -m 'Add some NewFeature')
4. Push to the Branch (git push origin feature/NewFeature)
5. Open a Pull Request

Tech Stacks/Tools Used

License

Project is available under the MIT license. See the LICENSE file for more info.

Author

Shaurya Choudhary