Low Speed Trading and Small in Budget; Large Expenses - A data science exercise project for stock market trading.
This is an programming and machine learning, in particular deep learning, exercise. The stage of this exercise is stock market trading.
You may want to follow the project or want more information:
Primary target group are traders, in particular individuals, who
- have limited time resources prohibiting them to look after their stocks
- only want to put a small amount of money at risk, and
- due to the bullet point above, experience high fees when trading. We will consider the fees as high, if the minimum transaction fee makes up a significant single digit percentage of the amount of invested capital for a stock. See wiki for an example.
Key takeaway
For low volume trading, the order fees reduce significantly the gross profit of the target group.
For this group of traders, LoSTanSiBLE aims to provide some algorithmic support. The objective is to make them successful at the stock market.
These instructions will get you a copy of the project up and running on your local machine for development and testing purposes. See deployment for notes on how to deploy the project on a live system.
You need the following softare preinstalled
- Docker
- Editor of your choice
A step by step series of examples that tell you how to get a development env running
git clone https://github.com/cdeck3r/LoSTanSiBLE.git
cd LoSTanSiBLE
Build the Docker image, target is lostansible:latest
./build.sh
Adapt docker run ... command to your needs in file lostansible.sh. Executing the script to spin up the container.
./lostansible.sh bash
End with an example of getting some data out of the system or using it for a little demo
make test
Run LoSTanSiBLE as it is in the dev environment. LoSTanSiBLE is intended to run on floydhub
If you like to contribute to the project, just submit a pull requests.
We use SemVer for versioning. For the versions available, see the tags on this repository.
- Christian Decker - Initial work
This project is licensed under the MIT License - see the LICENSE file for details
This project would not have been possible without the exceptional work of many others who have provided code .
- Jupyter and Python community
- Tensorflow and Keras community
- PurpleBooth for her README.md template
- waleedka's Dockerfile
- pjbull's cookiecutter for data science
If you feel, your part is not listed here, drop me a mail.