Dear Community Members,
Below is a mean reversion long-only backtest conducted on Accern Institutional historical data.
Accern is the world’s first big data media analytics provider to deliver the most comprehensive dataset of actionable and authentic stories and analytics from over 20 million news and blog sources for quantitative trading. With cutting-edge machine learning, deep learning, and neural network algorithms, we have designed actionable trading metrics for the quantitative trading space. We currently utilized the data as a standalone model, but it can be applied very successfully with any multi-factor models.
Alpha Institutional API Trading Metrics
Article Sentiment (1 to -1): Identifies the attitude the article is written in. This can be used as a directional signal.
Story Sentiment (1 to -1): Tracks the aggregated sentiment for a specific story. This can be used as a directional signal.
Source and Author Rankings
Overall Source Rank (1 - 10): Evaluates the credibility of a source based on its timeliness and re-post rate of releasing stories.
Event Source Rank (1-10): Evaluates the credibility of a source based on its timeliness and re-post rate of releasing stories on specific events.
Overall Author Rank (1 - 10): Evaluates the credibility of an author based on its timeliness and re-post rate of releasing stories.
Event Author Rank (1-10): Evaluates the credibility of an author based on its timeliness and re-post rate of releasing stories on specific events.
Market-Moving Event Ranks
Overall Event Impact Score (1-100): Probability that an event will have a greater-than-1% impact on any stock.
Entity Event Impact Score (1-100): Probability that an event will have a greater-than-1% impact on the mentioned stock.
Time and Exposure Analysis
Timeliness Of News
First Mention (TRUE/FALSE): Alerts you on unique story before they become exposed on the web.
Story Saturation (Low/Mid/High): Tracks the online exposure rate of a specific story. This can be used as an enter and/or exit signal.
We backtested a mean reversion long-only strategy from February 2016 to August 2016 using Accern’s historical news and blog dataset. We used the following metrics in our backtest: article_sentiment, event_impact_score_entity, and overall_source_rank.
We filtered the historical data to look at articles with:
- article_sentiment < -0.20
- event_impact_score_entity > 80
- overall_source_rank > 6
A weight multiplier was then applied to articles that matched the filtered criteria:
- event_impact_score: power of 33 (multiplies 33 times)
- article_sentiment: power of 12 (multiples 12 times)
The scores were then normalized so they added up to 1. The larger the score, the more shares we bought.
We conduct a backtest using daily, weekly, and monthly holding periods. The results differed based on holding periods.
BACKTEST REPORT (PDF)
HISTORICAL DATA FILE USED
FOR QUANT FUNDS INTERESTED
Contact [email protected] to request access to our 4 years of historical data (15 million articles) and our low-latency API feed for research and backtesting.
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|