[Quantopian Update] - This algorithm is now outdated. While we haven't replicated this algorithm, we've provided a few other examples using Accern's Alphaone data feed in strategies. Check out this Earnings Drift strategy using Accern for example.
We have recently backtested over 1.5 million news and blog articles (2.5 years length) with the help of Quantopian community members. We have received very positive results in the backtest and I would like to share it with you all.
The news and blog dataset was designed by Accern. Accern specialized in big data media analytics. We monitor over 20 million news and blog sources each day and provide over 25+ fields of analytics designed specifically for quantitative trading. Accern currently serve some of the largest multi-billion AUM hedge funds worldwide.
The fields of analytics used in this backtest chart are: Article Sentiment, Impact Score on Entity, and Overall Source Rank.
Article Sentiment (-1 – 1): This metric calculated the sentiment score of an article which is relevant to a company.
• A positive sentiment score means that the article was written in a positive tone towards a company. • A negative sentiment score means that the article was written in a negative tone towards a company. • This can be used as a directional trigger.
Overall Source Rank (0-10): This metric calculated the timeliness and reposting of a source; can be used as a trust factor and a viral factor.
• A high overall source rank means that source x is usually first at releasing articles before other sources and other sources usually repost the same information after source x has posted it. • A lower overall source rank means that source x is usually late at releasing articles before other sources and other sources usually never repost the same information after source x has posted it. • This can be used as a trust filter.
Impact Score on Entity (1-100): This metric calculated if the article will have a greater-than-1% impact on the stock on the same trading day.
• A high impact score means that the article has a high probably of affecting the stock price by more than 1%. • A low impact score means that the article has a low probably of affecting the stock price by more than 1%. • This can be used as a decision maker to execute an order.
The backtest report explains it in more details. Please review the report and share it with anyone you like. If you would like to have access to our 2.5 years of news and blog data, send me an email and I will provide you access. We want more of the community to conduct further test on the data to exploit it's value. We have just scratch the surface.
Request access to over 2.5 years of news and blog history (7.5 million articles) by sending an email to [email protected].
Co-Founder and CEO, Accern
|Returns||1 Month||3 Month||6 Month||12 Month|
|Alpha||1 Month||3 Month||6 Month||12 Month|
|Beta||1 Month||3 Month||6 Month||12 Month|
|Sharpe||1 Month||3 Month||6 Month||12 Month|
|Sortino||1 Month||3 Month||6 Month||12 Month|
|Volatility||1 Month||3 Month||6 Month||12 Month|
|Max Drawdown||1 Month||3 Month||6 Month||12 Month|