[Quantopian Update] - This algorithm is now outdated, please visit this thread to see recent examples of Accern's data with pipeline and Quantopian 2
Hi Quantopians,
We conducted a very brief market neutral backtest using our news and blog data. Our goal was to generate excessive return, while neutralizing risk (getting beta to 0), and maximizing our portfolio cash usage. We grouped stocks into bulls and bears section.
- We identified bull stocks to be long each week at market-open time at 9:30AM when a positively-toned story with high probability of impact is released.
- We identified bear stocks to be short each week at market-open time at 9:30AM when a negatively-toned story with high probability of impact is released.
We enter positions at the beginning of each week at 9:30 AM and exit all positions at the end of the week at 3:45PM.
Following metrics were used:
Story Sentiment (SS) (-1 – 1): This metric calculated the sentiment score of a story which was relevant to a company.
- A positive sentiment score meant that the story was trending positively.
- A negative sentiment score meant that the story was trending negatively
- This could be used as a directional trigger.
Event Impact Score on Entity (EIS) (1-100): This metric calculated if an article would have a greater-than-1% impact on the stock on the same trading day.
- A high impact score meant that the article had a high probability of affecting the stock price by more than 1%.
- A low impact score meant that the article had a low probability of affecting the stock price by more than 1%.
Buy if: Article Sentiment > 0.35 and Event Impact Score on Entity > 85
Sell if: Article Sentiment < -0.35 and Event Impact Score on Entity > 85
Attached is the full backtest report: Market-Neutral Backtest
Feel free to send me an email with questions: [email protected].
Best,
Kumesh Aroomoogan
Co-Founder & CEO, Accern