Skip to main content

🚀 MeridianAlgo Smart Trader

Ultra-Accurate AI Stock Analysis with Universal GPU Support

PyPI version Python 3.8+ License: MIT GPU Support

Professional-grade stock analysis powered by ensemble machine learning with universal GPU acceleration. Features advanced volatility spike detection and real-time technical analysis.

✨ Key Features

  • 🎯 Ultra-Accurate Predictions: Ensemble ML models (LSTM + Transformer + XGBoost)
  • 🔥 Universal GPU Support: AMD • Intel • NVIDIA • Apple Silicon
  • Volatility Spike Detection: Predict market turbulence before it happens
  • 📊 Real-time Analysis: Live market data with technical indicators
  • 🎨 Clean Output: Simplified, essential information only
  • 🚀 Easy Integration: Simple Python API and CLI

🚀 Quick Start

Installation

pip install meridianalgo-smarttrader

Command Line Usage

# Analyze Apple stock
smart-trader AAPL

# Custom parameters
smart-trader TSLA --days 90 --epochs 15

# Show GPU information
smart-trader --gpu-info

Python API Usage

from meridianalgo import SmartTrader, analyze_stock

# Simple analysis
result = analyze_stock('AAPL')
print(f"Current: ${result['current_price']:.2f}")
print(f"Tomorrow: ${result['predictions'][0]:.2f}")

# Advanced usage
trader = SmartTrader(verbose=True)
analysis = trader.analyze('TSLA', days=60, epochs=10)

# Check volatility spike risk
vol_risk = analysis['volatility_spike']['spike_probability']
if vol_risk > 60:
    print("⚠️ High volatility spike risk detected!")

📊 Sample Output

🚀 AAPL Analysis
Device: CPU (8 threads)

┌────────────┬──────────┬──────────────────┐
│ Metric     │ Value    │ Info             │
├────────────┼──────────┼──────────────────┤
│ Current    │ $213.96  │ Real-time        │
│ Day +1     │ $216.45  │ +1.2%            │
│ Day +2     │ $218.30  │ +2.0%            │
│ Day +3     │ $215.80  │ +0.9%            │
│ Confidence │ 84%      │ Model reliability│
│ Vol Risk   │ 23%      │ ✅ Low risk      │
└────────────┴──────────┴──────────────────┘

🔥 Universal GPU Support

Smart Trader automatically detects and optimizes for your GPU:

Vendor Technology Status
🟢 NVIDIA CUDA ✅ Supported
🔴 AMD ROCm/DirectML ✅ Supported
🔵 Intel XPU ✅ Supported
🍎 Apple MPS ✅ Supported

GPU Setup

# NVIDIA GPU
pip install torch torchvision torchaudio --index-url https://download.pytorch.org/whl/cu121

# AMD GPU (Windows)
pip install torch-directml

# Intel GPU
pip install intel-extension-for-pytorch

# Apple Silicon (automatic)
pip install torch torchvision torchaudio

⚡ Volatility Spike Detection

Smart Trader's advanced algorithm analyzes historical volatility patterns to predict future market turbulence:

from meridianalgo import detect_volatility_spikes
import yfinance as yf

# Get stock data
data = yf.Ticker('AAPL').history(period='1y')

# Detect volatility spikes
spike_info = detect_volatility_spikes(data)

print(f"Spike Probability: {spike_info['spike_probability']:.1f}%")
print(f"Expected in: {spike_info['expected_spike_days']} days")
print(f"Risk Level: {spike_info['risk_level']}")

🎯 Advanced Features

Ensemble Models

  • LSTM: Captures long-term dependencies
  • Transformer: Attention-based pattern recognition
  • XGBoost: Gradient boosting for robustness

Technical Indicators

  • RSI (Relative Strength Index)
  • MACD (Moving Average Convergence Divergence)
  • Bollinger Bands
  • Volume analysis

Risk Management

  • Volatility spike prediction
  • Market regime detection
  • Confidence scoring
  • Position sizing recommendations

📈 Performance

Metric CPU GPU
Training Time (10 epochs) ~2-3 seconds ~0.5-1 seconds
Batch Size 32 64+
Memory Usage 2-4 GB RAM GPU VRAM
Accuracy High Higher

🛠️ Development

Local Installation

git clone https://github.com/MeridianAlgo/In-Python.git
cd In-Python
pip install -e .

Running Tests

pytest tests/

Building Package

python setup.py sdist bdist_wheel
twine upload dist/*

📚 Documentation

🤝 Contributing

We welcome contributions! Please see our Contributing Guide for details.

📄 License

This project is licensed under the MIT License - see the LICENSE file for details.

🔗 Links

🏆 About MeridianAlgo

MeridianAlgo specializes in advanced financial AI solutions. Our mission is to democratize professional-grade trading tools through cutting-edge machine learning and universal GPU acceleration.


Made with ❤️ by MeridianAlgo

Empowering traders with AI-driven insights

Download files

Download the file for your platform. If you're not sure which to choose, learn more about installing packages.

Source Distribution

meridianalgo_smarttrader-1.0.0.tar.gz (79.0 kB view details)

Uploaded Source

Built Distribution

If you're not sure about the file name format, learn more about wheel file names.

meridianalgo_smarttrader-1.0.0-py3-none-any.whl (18.4 kB view details)

Uploaded Python 3

File details

Details for the file meridianalgo_smarttrader-1.0.0.tar.gz.

File metadata

  • Download URL: meridianalgo_smarttrader-1.0.0.tar.gz
  • Upload date:
  • Size: 79.0 kB
  • Tags: Source
  • Uploaded using Trusted Publishing? No
  • Uploaded via: twine/6.1.0 CPython/3.13.5

File hashes

Hashes for meridianalgo_smarttrader-1.0.0.tar.gz
Algorithm Hash digest
SHA256 e11db48fe820e5df1b07ee265243f47f267111d2202aebf02a28f1b630bd76fe
MD5 4006e6a053a5c7e8d6f10425a41352cf
BLAKE2b-256 f805d8786d225ef41d35c581af9b8cbabfdbe1961eb9aad0e4ed9b4d06c96fbb

See more details on using hashes here.

File details

Details for the file meridianalgo_smarttrader-1.0.0-py3-none-any.whl.

File metadata

File hashes

Hashes for meridianalgo_smarttrader-1.0.0-py3-none-any.whl
Algorithm Hash digest
SHA256 636366d625c850844ea5d7f202e0b002429bd01ad540ad9e8103b0db9cb481a6
MD5 cbcbd77c044e6ba2eb370c27aad7c443
BLAKE2b-256 70587a6cf040d5a8b23f1c2c968c4fc97ea2e84ebd7d181743eaddaaeff02035

See more details on using hashes here.

Release history Release notifications | RSS feed

This release

1.0.0 This release

2 files

Supported by

AWS Cloud computing and Security Sponsor Datadog Monitoring Depot Continuous Integration Fastly CDN Google Download Analytics Sentry Error logging StatusPage Status page