Popular Community Posts¶
One of the best features of the Quantopian community forums is the ability to share research and ideas in the form of Research notebooks. This section of the cookbook links to some of the best case studies and research projects shared in the forums.
Studies Using Built-In Data¶
The following studies were conducted using datasets built-in to the Quantopian platform. These studies can be cloned and run in the Research environment or IDE (depending on whether the content is in the form of a notebook or algorithm).
Momentum With Volatility Timing¶
This post by community member Yulia Malitskaia features the Quantopian-based research presented in her paper "Momentum with Volatility Timing” (SSRN: http://ssrn.com/abstract=3417360). Specifically, the paper introduces the volatility-timed winners approach that applies past volatilities as a timing predictor to mitigate momentum factor underperformance for time intervals spanning the market downturn and post-crisis period.
Pairs Trading With Machine Learning¶
This study walks through an example implementation of finding eligible pairs using Machine Learning and pricing data.
Studies Using Self-Serve Data¶
The following studies were conducted using custom datasets (uploaded using Self-Serve). Since Self-Serve datasets are currently private, there is usually a step involved to get the data setup on your local machine before you can clone and run the study.
Political Campaign Contributions¶
This study analyzes the impact of contributions from politicians toward publicly traded companies.
"Lazy Prices": Finding Alpha in 10K and 10Q Text Changes¶
This study looks at the effect of text changes in consecutive 10K and 10Q reports.
Pairs Trading With Natural Language Processing¶
This study walks through an example implementation of finding eligible pairs using Machine Learning and text-based company descriptions. Note that this post was made prior to the existence of Self-Serve Data so it uses an older feature,
local_csv to upload the custom data.
Techniques & Recipes¶
There are several posts in the community forums that offer ideas for improving your algorithms or research workflow. Below is a list of posts that share techniques and code examples that you may want to consider using in your own work.
This post shares an updated way of analyzing factors. The notebook contains some new thoughts on what constitutes a good factor and tips on how to build it and analyze it with a focus on certain alphalens features.
This post shares a notebook that allows you to check the correlation between two alpha factors, plus run an alpha factor through Pyfolio to see what the risk exposures look like.
This notebook illustrates how the TA-Lib (technical analysis library) with the Pipeline API.
New Release Notebooks¶
Often times, Quantopian employees will share notebooks that introduce a new platform feature. Below is a list of "new release" notebooks shared in the community forums by Quantopian employees.
This notebook was shared when the Optimize API was first released. The notebook walks through the math behind portfolio optimization as well as some portfolio construciton examples.
This notebook explores the mathematical and computational components of the beta-to-SPY computation. The notebook focuses on building a faster (but still accurate) beta-to-SPY computation in Pipeline. The result is the
This notebook introduces the Quantopian Risk Model and demonstrates how it can be used in Research.
When the Self-Serve Data feature was added to Quantopian, there were 2 notebooks published to explain what the feature is and how it works.
Since 2018, Quantopian has been adding and improving support for global equity research by providing data for equity markets all over the world. Below are some announcement posts discussing global equity data on Quantopian.
Pyfolio is an open source library managed by Quantopian for performance and risk analysis. Pyfolio allows you to easily generate plots and information about a stock, portfolio, or algorithm.