ThroneTrader

A collection of algorithms to analyze, categorize and predict stocks.

These algorithms are used to assess stocks, and make predictions about future stock prices.

The collection of algorithms leverage data analysis, machine learning, and statistical methods to achieve its objectives in the context of financial markets and investments.

Installation

python -m pip install throne-trader

Usage

Predict future stock prices using machine learning

from thronetrader import Predictions

predictions = Predictions(symbol="AAPL")
print(predictions.linear_regression_prediction())
print(predictions.gradient_boosting_prediction())

Generate buy/sell/hold signals based on real-time data

from thronetrader import RealTimeSignals

realtime_signals = RealTimeSignals(symbol="AAPL")

print(realtime_signals.get_financial_signals())
print(realtime_signals.get_insider_signals())

series1, series2 = realtime_signals.get_trading_volume()
print(series1.name)
print(series1.to_dict())
print(series2.name)
print(series2.to_dict())

Generate buy/sell/hold signals based on strategic algorithms

from thronetrader import StrategicSignals

strategic_signals = StrategicSignals(symbol="AAPL")

print(strategic_signals.get_bollinger_bands_signals())
print(strategic_signals.get_breakout_signals())
print(strategic_signals.get_crossover_signals())
print(strategic_signals.get_macd_signals())
print(strategic_signals.get_rsi_signals())

💡 While individual algorithms may lack optimal accuracy, the aggregation of multiple algorithms proves valuable and effective in enhancing overall prediction accuracy.

⚠️ Please note that stock prediction is inherently challenging, and the accuracy of any prediction model will depend on the quality and relevance of the data used, the choice of algorithms, and the changing dynamics of the stock market. Continuous evaluation and improvement of the model are essential to enhance its predictive capabilities.

Components

• Predict stock price using deep learning models
• Analyze stock price using machine learning models
• Generate buy/sell/hold signals using real time data
• Generate buy/sell/hold signals using financial strategies

Sample Notebooks

• Long Short-Term Memory
• Gradient Boosting
• Linear Regression

Disclaimer

Remember to thoroughly backtest and paper trade any strategy before using real funds, and always exercise caution and risk management when trading stocks.

Coding Standards

Docstring format: Google
Styling conventions: PEP 8
Clean code with pre-commit hooks: flake8 and isort

Release Notes

Requirement

python -m pip install gitverse

Usage

gitverse-release reverse -f release_notes.rst -t 'Release Notes'

Linting

PreCommit will ensure linting, and the doc creation are run on every commit.

Requirement

pip install sphinx==5.1.1 pre-commit recommonmark pytest

Usage

pre-commit run --all-files

Pypi Package

Runbook

License & copyright

© Vignesh Rao

Licensed under the MIT License