About 4 months ago, we announced that we were hard at work building a hosted research platform for analyzing our curated datasets, your Quantopian algorithms, and your backtest results.
For the first time, we want to share a notebook here in the forums to give you a sneak peek into how the research platform is progressing and more importantly how it can help you craft better trading algorithms.
We collaborated with EventVestor, a data vendor who provides information about corporate events. Specifically, EventVestor has provided us with data on share buyback announcements. In the notebook, we explore the idea of a post-share buyback announcement drift in stocks. We load raw data from EventVestor into the notebook and dig into the various attributes provided by the data to better understand our options when building an algorithm. With that knowledge in hand, having built an algorithm to use the data, we then explore the results from each variation.
Below is a chart from the notebook that summarizes our findings. We're able to optimize our parameters through the course of the notebook. We find the optimal combination of variables for maximizing returns, maximizing Sharpe ratio and minimizing drawdown.
Click the "VIEW NOTEBOOK" button and scroll through the notebook to see our step by step process for testing and optimizing our strategy.
The algorithm used for this analysis is found on this thread, please scroll down to find the backtest.
The sample data in this algorithm provides a static snapshot between January 2007 - January 2015. That being said, fetch_eventvestor is not allowed in Live Trading and your algorithm will throw an error if you try to deploy it in either paper, context, or live trading modes!
We are working to incorporate this data in a more permanent fashion but until then, you can contact EventVestor for more information.
If you'd like to look at the drift found in this event, you can find the followup event study here.