Ecosyste.ms: Awesome

An open API service indexing awesome lists of open source software.

Awesome Lists | Featured Topics | Projects

https://github.com/stephanakkerman/tensortrade

This repository contains my TensorTrade-focused code, including the core program and supplemental tools used in my bachelor's thesis on trading low market capitalization cryptocurrencies using reinforcement learning.
https://github.com/stephanakkerman/tensortrade

automated-trading automated-trading-bot benchmark binance crypto cryptocurrency heatmap python reinforcement-learning tensorflow tensortrade

Last synced: 2 months ago
JSON representation

Host: GitHub
URL: https://github.com/stephanakkerman/tensortrade
Owner: StephanAkkerman
License: mit
Created: 2021-04-03T15:39:04.000Z (almost 4 years ago)
Default Branch: main
Last Pushed: 2023-05-16T15:47:55.000Z (over 1 year ago)
Last Synced: 2024-05-02T00:56:55.212Z (9 months ago)
Topics: automated-trading, automated-trading-bot, benchmark, binance, crypto, cryptocurrency, heatmap, python, reinforcement-learning, tensorflow, tensortrade
Language: Python
Homepage:
Size: 545 KB
Stars: 34
Watchers: 3
Forks: 12
Open Issues: 1
Metadata Files:
- Readme: README.md
- License: LICENSE

Awesome Lists containing this project

README

# TensorTrade
[![Python 3.7](https://img.shields.io/badge/python-3.7-blue.svg)](https://www.python.org/downloads/release/python-380/)
[![Code style: black](https://img.shields.io/badge/code%20style-black-000000.svg)](https://github.com/psf/black)
[![MIT License](https://img.shields.io/github/license/StephanAkkerman/TensorTrade.svg?color=brightgreen)](https://opensource.org/licenses/MIT)

---

This is the reinforcement learning code I used for my thesis about how to trade low market capitulization cryptocurrencies.

## Features
- Fetches up to date historical data from Binance, using a custom script.
- Plots a comparison of the reinforcement learning agent and simple trading strategies (see section Images for more info).
- Some extras, such as an analysis of all TA indicators available for the TA library.

## Dependencies
The required packages to run this code can be found in the `requirements.txt` file. To run this file, execute the following code block:
```
$ pip install -r requirements.txt
```
Alternatively, you can install the required packages manually like this:
```
$ pip install
```

## How to run
- Clone the repository
- Run `$ python src/main.py`
- See result

# Images
## Comparison
After testing the RL agent a graph is plotted, showing the net worth of the agent compared to the benchmarks.
![Image of benchmark](https://github.com/StephanAkkerman/TensorTrade/blob/main/img/Picture1.png)

## TACorrelation
Displays a heatmap of absolute correlation of technical analysis indicators in the same group.
This is how the heatmap of trend indicators looks like.

![Image of heatmap](https://github.com/StephanAkkerman/TensorTrade/blob/main/img/Trend_heatmap.png)