Rebalance Ep 16: Hidden Markov Models

Rebalance is a weekly flash briefing of new features and updates for you, our QC community. In our 16th episode we’re happy to share:

  • Documentation improvements! We added a table of contents for each page, allowing you to find topics you are looking for faster. We’re also installing new search technology which will help you find relevant documentation. Additionally, Gerardo was hard at work making demonstration research notebooks for all the alternative data vendors we support.
  • Easier history DataFrame indexing! We’ve improved pandas data series access. Now history results can use a Symbol object as a key while using the iloc and loc indexers.
  • A better user experience with Interactive Brokers data requests! You’ll see a reduction in the frequency of timeouts with Interactive Brokers’ data requests for futures and options. Our team worked to request the right tick types and more intelligently handle rate limit errors from the IBGateway.
  • A new “From Research to Production” post! This week Jack walks us through a strategy using Hidden Markov Models to represent the market shift from bull to bear and to predict the market state. A Markov process is stochastic where the possibility of switching to another state depends only on the current state of the model. Dive into the concept and clone the template in the link here.
Sherry Yang

By: Sherry Yang

27.11.2019