QuantConnect Local Platform

QuantConnect is a cloud-hosted algorithmic trading platform with a vibrant community. Our community writes over 1M lines of code monthly and processes $1-2B in live trading volume through our cloud-hosted platform. Our cloud platform provides hundreds of terabytes of financial data, training material, and turn-key quant trading experience.

The QuantConnect Local Platform is an on-premise version of this cloud technology that provides more flexibility and control over the research process. The technology is delivered through a VSCode extension with the research running in Docker containers. With the Local Platform, you can use version control, coding tools, custom packages, and proprietary datasets on-premise.

The core technology powering this is called LEAN. LEAN is an open-source algorithmic trading engine that handles all the data loading, connectivity, and modeling of financial asset portfolios.

Our plugin automatically syncs cloud and local codebases, letting you backtest, deploy research notebooks, or live trade in either location. If you don't have data or computing power locally, deploy it to the cloud for a faster result. Want more fine-grained control over your backtest? Code locally with Copilot, and backtest on-premise. The Local Platform is compliance-friendly and has full feature parity with our cloud environment.

The Local Platform is a paid feature of QuantConnect. It can use cloud servers with a $10/mo Researcher subscription. To use it entirely on-premise with your own data requires an Institutional subscription to support the open-source project. If you'd like to use QC/LEAN on-premise without supporting the open-source, you can clone LEAN.

Setup & Requirements

A QuantConnect subscription is required to use the Local Platform. All subscriptions can access subscribed cloud resources from on-premise installations. An Institutional subscription is needed for on-premise research, backtesting, optimization, and live trading.

We run all algorithms in a Docker container to avoid installing any dependencies on your computer. The extension scans for a valid Docker installation and will prompt you to install it if not detected.

Roadmap

The Local Platform has achieved feature parity with the QuantConnect Cloud and will have matching feature sets.

Projects

Easily create new algorithms, synchronize code with the cloud, and clone projects with the Local Platform -- all with full local autocomplete. Projects contain files to run backtests, launch research notebooks, perform parameter optimizations, and deploy live trading strategies. Create strategies and share your work with other members. Work with code external libraries and share code with collaborators.

Read more about projects in our documentation.

Backtesting

Backtesting is the process of simulating a trading algorithm on historical data. By running a backtest, you can measure how the algorithm would have performed in the past. Although past performance doesn't guarantee future results, an algorithm with a proven track record can provide investors with more confidence when deploying to live trading than an algorithm that hasn't performed favorably. Use the QuantConnect platform to run backtests on institutional-grade datasets and an open-source backtesting engine that's being improved constantly. Use fast cloud servers to execute the backtests, and the backtesting hardware is maintained 24/7 by QuantConnect engineers.

Read more about backtesting in our documentation.

Research

The Research Environment is a Jupyter notebook-based environment where you can access our data through the QuantBook class instead of through the QCAlgorithm class in a backtest. The environment supports both Python and C#. If you use Python, you can import code from the code files in your project into the Research Environment to aid development. Train heavy machine-learning tasks offline and deploy the models to live trading through the QuantConnect Object Store.

Read more about research in our documentation.

Optimization

Parameter optimization is the process of finding the optimal algorithm parameters to maximize or minimize an objective function. For instance, you can optimize your indicator parameters to maximize the Sharpe ratio that your algorithm achieves over a backtest. Optimization can help you adjust your strategy to achieve better backtesting performance.

Read more about optimization in our documentation.

.

Live Trading

A live algorithm is an algorithm that trades in real time with real market data. QuantConnect Cloud lets you run your algorithms live with real-time market data on our battle-tested infrastructure. We have hosted over 200,000 live algorithms and trade more than $2B monthly volume. With the Local Platform, you can self-host these strategies to use local data feeds and trading interfaces.

Read more about live trading in our documentation.

Datasets

Access data from Our Dataset Market for you to use in your algorithms from the Local Platform. Our Dataset Market includes price, fundamental, and alternative datasets. The Dataset Market lets you easily load datasets into your trading algorithms for use in the cloud or locally. Data is ready to use, without cleaning or ETL needed. The datasets in our market are vetted by the QuantConnect team to be high-quality, contain actionable information, and be free of survivorship bias.

Read more about datasets in our documentation.

Support

For more support, please submit a ticket at https://www.quantconnect.com/support or to support@quantconnect.com

Contact Us

We'd love to hear your feedback and ideas. Please drop us a line at support@quantconnect.com.