Package Exports

neural-trader
neural-trader/index.js

This package does not declare an exports field, so the exports above have been automatically detected and optimized by JSPM instead. If any package subpath is missing, it is recommended to post an issue to the original package (neural-trader) to support the "exports" field. If that is not possible, create a JSPM override to customize the exports field for this package.

Readme

neural-trader

Complete Neural Trader platform - all features included. This meta-package installs all Neural Trader components for a full-featured algorithmic trading system powered by Rust.

Features

Complete Platform: All 13 Neural Trader packages in one install
Zero Configuration: Works out of the box
Rust Performance: Native bindings for maximum speed
Professional Tools: Everything from backtesting to live trading
150+ Indicators: Comprehensive technical analysis
Neural Networks: State-of-the-art ML models
Risk Management: VaR, CVaR, Kelly Criterion, and more

Installation

npm install neural-trader

This installs all packages:

@neural-trader/core - Core types and interfaces
@neural-trader/backtesting - High-performance backtesting engine
@neural-trader/neural - Neural network models
@neural-trader/risk - Risk management toolkit
@neural-trader/strategies - Trading strategies
@neural-trader/portfolio - Portfolio management
@neural-trader/execution - Order execution
@neural-trader/brokers - Broker integrations
@neural-trader/market-data - Market data providers
@neural-trader/features - Technical indicators
@neural-trader/sports-betting - Sports betting tools
@neural-trader/prediction-markets - Prediction markets
@neural-trader/news-trading - News-driven trading

Quick Start

import {
  BacktestEngine,
  NeuralModel,
  RiskManager,
  StrategyRunner,
  PortfolioManager,
  BrokerClient,
  MarketDataProvider
} from 'neural-trader';

// Everything you need in one import!

// 1. Set up market data
const dataProvider = new MarketDataProvider({
  provider: 'alpaca',
  apiKey: process.env.ALPACA_KEY,
  apiSecret: process.env.ALPACA_SECRET,
  websocketEnabled: true
});

await dataProvider.connect();

// 2. Create trading strategy
const strategyRunner = new StrategyRunner();
await strategyRunner.addMomentumStrategy({
  name: 'SMA Crossover',
  symbols: ['AAPL', 'MSFT', 'GOOGL'],
  parameters: JSON.stringify({ shortPeriod: 20, longPeriod: 50 })
});

// 3. Set up risk management
const riskManager = new RiskManager({
  confidenceLevel: 0.95,
  lookbackPeriods: 252,
  method: 'historical'
});

// 4. Backtest strategy
const backtestEngine = new BacktestEngine({
  initialCapital: 100000,
  startDate: '2023-01-01',
  endDate: '2023-12-31',
  commission: 0.001,
  slippage: 0.0005,
  useMarkToMarket: true
});

const signals = await strategyRunner.generateSignals();
const result = await backtestEngine.run(signals, 'market-data.csv');

console.log(`Sharpe Ratio: ${result.metrics.sharpeRatio.toFixed(2)}`);
console.log(`Total Return: ${(result.metrics.totalReturn * 100).toFixed(2)}%`);
console.log(`Max Drawdown: ${(result.metrics.maxDrawdown * 100).toFixed(2)}%`);

// 5. Train neural model
const model = new NeuralModel({
  modelType: 'LSTMAttention',
  inputSize: 20,
  horizon: 5,
  hiddenSize: 128,
  numLayers: 3,
  dropout: 0.2,
  learningRate: 0.001
});

await model.train(trainingData, targets, {
  epochs: 100,
  batchSize: 32,
  validationSplit: 0.2,
  earlyStoppingPatience: 10,
  useGpu: true
});

// 6. Connect to broker for live trading
const broker = new BrokerClient({
  brokerType: 'alpaca',
  apiKey: process.env.ALPACA_KEY,
  apiSecret: process.env.ALPACA_SECRET,
  paperTrading: true
});

await broker.connect();

// 7. Manage portfolio
const portfolio = new PortfolioManager(100000);

// You're ready to trade!

What's Included

Core & Infrastructure

@neural-trader/core: TypeScript types and interfaces (zero dependencies)
@neural-trader/execution: Smart order execution with TWAP/VWAP
@neural-trader/brokers: Alpaca, Interactive Brokers, TD Ameritrade integration

Data & Analysis

@neural-trader/market-data: Real-time and historical market data
@neural-trader/features: 150+ technical indicators
@neural-trader/backtesting: Lightning-fast backtesting engine

Trading & Strategy

@neural-trader/strategies: Momentum, mean reversion, pairs trading
@neural-trader/portfolio: Portfolio optimization and management
@neural-trader/risk: VaR, CVaR, Kelly Criterion, Sharpe/Sortino

Advanced Features

@neural-trader/neural: LSTM, Transformer, N-HiTS models
@neural-trader/sports-betting: Arbitrage and Kelly sizing
@neural-trader/prediction-markets: Polymarket and Augur (coming soon)
@neural-trader/news-trading: Sentiment analysis (coming soon)

Platform Requirements

Node.js: 16.x or higher
Operating System: Linux, macOS, or Windows
Optional: CUDA 11+ for GPU acceleration

Documentation

Each package includes comprehensive documentation:

Examples

See the examples directory for:

Complete trading systems
Strategy development tutorials
Backtest optimization
Live trading setup
Neural network training

Support

Documentation: https://github.com/ruvnet/neural-trader
Issues: https://github.com/ruvnet/neural-trader/issues
Discussions: https://github.com/ruvnet/neural-trader/discussions

License

This package is dual-licensed under MIT OR Apache-2.0.

MIT License: https://opensource.org/licenses/MIT Apache-2.0 License: https://www.apache.org/licenses/LICENSE-2.0

You may choose either license for your use.

Built with Rust 🦀 | Powered by Neural Networks 🧠 | Ready for Production ✨