AI-Scalpel-Trading-Bot

Disclaimer

This software is for educational purposes only. Do not risk money which you are afraid to lose. USE THE SOFTWARE AT YOUR OWN RISK. THE AUTHORS AND ALL AFFILIATES ASSUME NO RESPONSIBILITY FOR YOUR TRADING RESULTS.

Always start by running a trading bot in Dry-run and do not engage money before you understand how it works and what profit/loss you should expect.

This is an implementation of freqtrade where different machine learning implementations will be tested.

Freqtrade is a free and open source crypto trading bot written in Python. It is designed to support all major exchanges and be controlled via Telegram. It contains backtesting, plotting and money management tools as well as strategy optimization by machine learning.

Exchange marketplaces supported

Bittrex
Binance (*Note for binance users)
113 others to tests. (Some of them might not work)

Documentation

Documentation.

Features

Quick start

Freqtrade provides a Linux/macOS script to install all dependencies and help you to configure the bot.

git clone git@github.com:freqtrade/freqtrade.git
cd freqtrade
git checkout develop
./setup.sh --install

Other installations.

Basic Usage

Bot commands

usage: freqtrade [-h] [-v] [--logfile FILE] [--version] [-c PATH] [-d PATH]
                 [-s NAME] [--strategy-path PATH] [--dynamic-whitelist [INT]]
                 [--db-url PATH] [--sd-notify]
                 {backtesting,edge,hyperopt} ...

Free, open source crypto trading bot

positional arguments:
  {backtesting,edge,hyperopt}
    backtesting         Backtesting module.
    edge                Edge module.
    hyperopt            Hyperopt module.

optional arguments:
  -h, --help            show this help message and exit
  -v, --verbose         Verbose mode (-vv for more, -vvv to get all messages).
  --logfile FILE        Log to the file specified
  --version             show program's version number and exit
  -c PATH, --config PATH
                        Specify configuration file (default: None). Multiple
                        --config options may be used.
  -d PATH, --datadir PATH
                        Path to backtest data.
  -s NAME, --strategy NAME
                        Specify strategy class name (default:
                        DefaultStrategy).
  --strategy-path PATH  Specify additional strategy lookup path.
  --dynamic-whitelist [INT]
                        Dynamically generate and update whitelist based on 24h
                        BaseVolume (default: 20). DEPRECATED.
  --db-url PATH         Override trades database URL, this is useful if
                        dry_run is enabled or in custom deployments (default:
                        None).
  --sd-notify           Notify systemd service manager.

Telegram RPC commands

Telegram is not mandatory. However, this is a great way to control your bot. More details on our documentation

/start: Starts the trader
/stop: Stops the trader
/status [table]: Lists all open trades
/count: Displays number of open trades
/profit: Lists cumulative profit from all finished trades
/forcesell <trade_id>|all: Instantly sells the given trade (Ignoring minimum_roi).
/performance: Show performance of each finished trade grouped by pair
/balance: Show account balance per currency
/daily <n>: Shows profit or loss per day, over the last n days
/help: Show help message
/version: Show version

Development branches

The project is currently setup in two main branches:

develop - This branch has often new features, but might also cause breaking changes.
master - This branch contains the latest stable release. The bot 'should' be stable on this branch, and is generally well tested.
feat/* - These are feature branches, which are being worked on heavily. Please don't use these unless you want to test a specific feature.

A note on Binance

For Binance, please add "BNB/<STAKE>" to your blacklist to avoid issues. Accounts having BNB accounts use this to pay for fees - if your first trade happens to be on BNB, further trades will consume this position and make the initial BNB order unsellable as the expected amount is not there anymore.

Support

Help / Slack

For any questions not covered by the documentation or for further information about the bot, I encourage you to join freqtrade's slack channel.

Click here to join Slack channel.

Bugs / Issues

If you discover a bug in the bot, please search their issue tracker first. If it hasn't been reported, please create a new issue and ensure you follow the template guide so that our team can assist you as quickly as possible.

Feature Requests

Have you a great idea to improve the bot you want to share? Please, first search if this feature was not already discussed. If it hasn't been requested, please create a new request and ensure you follow the template guide so that it does not get lost in the bug reports.

Pull Requests

Feel like the bot is missing a feature? Keep em pull requests coming!

Please read the Contributing document to understand the requirements before sending pull-requests.

Coding is not a neccessity to contribute - maybe start with improving our documentation? Issues labeled good first issue can be good first contributions, and will help get you familiar with the codebase.

Note before starting any major new feature work, please open an issue describing what you are planning to do or talk to the team on Slack. This will ensure that interested parties can give valuable feedback on the feature, and let others know that you are working on it.

Important: Always create your PR against the develop branch, not master.

Requirements

Uptodate clock

The clock must be accurate, syncronized to a NTP server very frequently to avoid problems with communication to the exchanges.

Min hardware required

To run this bot we recommend you a cloud instance with a minimum of:

Minimal (advised) system requirements: 2GB RAM, 1GB disk space, 2vCPU

Software requirements

Python 3.6.x
pip
git
TA-Lib
virtualenv (Recommended)
Docker (Recommended)

t3ch9/AI-Scalpel-Trading-Bot