Open Source Algorithmic Trading Platforms

On over 800 pages, this revised and expanded 2nd edition demonstrates how ML can add value to algorithmic trading through a broad range of applications. Organized in four parts and 24 chapters, it covers the end-to-end workflow from data sourcing and model development to strategy backtesting and evaluation. Covers key aspects of data sourcing, financial feature engineering, and portfolio management. The design and evaluation of long-short strategies based on a broad range of ML algorithms, how to extract tradeable signals from financial text data like SEC filings, earnings call transcripts or financial news. Using deep learning models like CNN and RNN with financial and alternative data, and how to generate synthetic data with Generative Adversarial Networks, as well as training a trading agent using deep reinforcement learning.

Automated accounting for splits, dividends, and corporate events like delistings and mergers. Avoid selection bias with dynamically generated assets. Create and select asset universes on proprietary data and indicators. Automatically track portfolio performance, profit and loss, and holdings across multiple asset classes and margin models in the same strategy. Trigger regular functions to occur at desired times, during market hours, on certain days of the week, or at specific times of day. Backtest on almost any time series and import your proprietary signal data into your strategy. Everything is configurable and pluggable. LEAN's highly modular foundation can easily be extended for your fund focus. Use combinations of margin, fill, and slippage models to simulate a liquidity endpoint. 100+ popular technical indicators built, tested, and ready for use. Applicable to any data source.

This project is no longer supported. We are working on a new algorithmic trading platform with extreme fast execution speed and lots of cool features. Please visit http://www.algospace.com/ for more detail.

An open source initiative for developing a scalable, high-speed trading desk. The Open Trading Desk will support trading in a variety of markets, to include: equities, options, mutual funds and ETFs, Forex, Bonds and Algorithmic trading.

An open-source framework for financial time-series analysis and algorithmic trading, based on Java and OSGi, with an Eclipse front-end. * Highly modular: usable as plain java API, OSGi components, or integrated into Eclipse * Standalone or client-server architecture, depending on performance and reliability needs * Integrated with Interactive Brokers through IB Java API * Generic broker API, it can easily be extended to work with other brokers * It works with historical and/or realtime market data * Backtesting facility * Extensible SWT charting library

Zipline is a Pythonic algorithmic trading library. It is an event-driven system for backtesting. Zipline is currently used in production as the backtesting and live-trading engine powering Quantopian -- a free, community-centered, hosted platform for building and executing trading strategies. Quantopian also offers a fully managed service for professionals that includes Zipline, Alphalens, Pyfolio, FactSet data, and more. Installing Zipline is slightly more involved than the average Python package. For a development installation (used to develop Zipline itself), create and activate a virtualenv, then run the etc/dev-install script. Please note that Zipline is not a community-led project. Zipline is maintained by the Quantopian engineering team, and we are quite small and often busy.