Rebalance Ep 11: Probabilistic Sharpe Ratio
Rebalance is a weekly flash briefing of new features and updates for you, our QC community. In our eleventh episode we’re happy to share:
- Our new Alpha performance metric, the Probabilistic Sharpe Ratio, is live! The PSR displayed with your backtest results is the confidence the Sharpe Ratio is greater than 1 based on the returns distribution. The PSR confidence is based on the distribution of daily returns of your strategy. See it in action on your next algorithm in the terminal!
- A new feature for your machine learning models! This week we shipped a feature that allows you to train your machine learning models in QuantConnect! The Train() method allows running blocks of code for up to 2 hours, giving you time to set up your machine learning state. Find the script here. We currently support the machine learning libraries Keras, Tensorflow and Theano.
- New algorithm templates with the theme “From Research to Production”! Each post highlights how you can seamlessly shift from the QC research environment to your backtests. Start with one of these topics: Mean Reversion or Random Forest Regression. Simply clone a template to get started!
- A new Boot Camp on the QC Algorithm Framework is out! The Algorithm Framework is the scaffolding for reusable module design. In the lesson, we focus on the creation of an Alpha Model to return insights based on a 14-day momentum indicator.