Social Market Analytics Identifies Most Accurate Twitter Accounts

Social Market Analytics aggregates the intentions of professional investors as expressed on Twitter.  We identify these professional investors using our proprietary twelve factor ranking system.  One factor is the forward accuracy of Twitter accounts.  If a Twitter account is Tweeting bullishly based on our patented NLP process and the security subsequently moves higher over specified periods that account is deemed to be accurate over that period.  Overall accuracy is aggregated across time for each account.  We have been tracking account accuracy out-of-sample for the past seven years. – it is impossible to recreate this data.  SMA is the only provider with out-of-sample account accuracy.  We found significant variability in account accuracy for supposed professional investors.  Social Market Analytics account scoring algorithms are extremely effective in excluding non-professional professionals.

SMA’s Accurate Account algos aggregate expectations from the most accurate Twitter accounts for individual securities for a specified time period: 1-Day, 2-Day, 1-Week, and 1-Month holding periods.   Definition of ‘Accurate’ – correctly identifying directional movement of the security’s price.  We do not include size of move – their sentiment is positive and the security moved higher.

We calculate consensus expectations of these accurate accounts on individual securities.  Accurate account universes differ across holding periods. Some accounts are more accurate in the short-term (Day trades), while others are more accurate for longer holding periods (up to one month).

Securities with significant consensus for both long and short are available through our API’s, Widgets and in Reports.  Below is a widget identifying securities with the most positive and negative consensus.   In this example, SMA’s accurate account universe is currently 100 bullish on MCO over the next 24 hrs.  Positive, negative and neutral are identified separately.

accurate accounts

To discuss getting access to these or any other SMA data feed or widget please contactus@socialMarketAnalytics.com

Thanks,

Joe

Social Market Analytics Receives Second Patent

Most of my blogs center around the predictive nature of Social Market Analytics data. This blog is different.  At Social Market Analytics we are continuously expanding and improving our technology.  These innovations sometime lead to such unique technology that a patent application is warranted.  As many of you know this is a lengthy and challenging process.  We are proud to announce SMA recently received our second patent as an extension of our original patent.  SMA now has two granted U.S. Patents.

Patent

Our first Patent was on our three-component system for extraction, evaluation and publication of metrics on social media feeds. The high-level diagram with Twitter as an input is below.

process

Each process above uses SMA created technology.  Extractor allows for the rapid ingestion of data.  Evaluator filters noise on both the author and content level and Calculator creates custom predictive metrics for multiple time frames and purposes.  As our processes evolve we apply for patents to protect this unique technology.  Our second granted U.S. Patent revolves around publication of metrics and alerting customers to breaking information available through our Twitter metrics and other sources. Although, we are exciting about our 2nd U.S. Patents, we already have our 3rd patent application in preparation!

Thanks for reading,

Joe

 

Introducing the Social Market Analytics (SMA) 50 Long Index

Social Market Analytics has been creating security level sentiment metrics for six years.  As we build an out-of-sample history we are able to build longer holding period indexes. I have blogged about longer term factors before, this is the most comprehensive portfolio strategy built using sentiment level data.  This blog will discuss the application of sentiment to a long only 50 stock, re balanced annually, index.

SMA50 Index is a new, capitalization weighted index comprised of 50 stocks with these features:

  1. The highest average unique message source counts, from SMA’s filtered Twitter data stream, observed over a 50-day look back interval, and
  2. High daily average dollar trading volume (ADV), > $20 Mil, over a 50-day look back interval.  We are looking for liquid stocks.

The SMA50 index measures the aggregate performance of stocks with high levels of crowd sourced commentary and high market liquidity.

  1. SMA50 is reconstituted each year on March 15th.  The core constituents are selected once a year.  They are re-weighted monthly based on the below tilt methodologies.
  2. SMA50 is the “Parent Index” for SMA50 Factor Tilt Products

Below is the historical performance of the SMA50 Index.  We will add tilting to the index based on sentiment and momentum.

SMA501

The following factor tilt indexes are derived from the equity universe of the SMA50 parent index.  Factor Tilt Indexes are re-balanced monthly on the first market day of the month.

SMA-MT: Momentum Tilt

– Designed to deliver the performance of an equity momentum strategy by emphasizing stocks with high risk-adjusted price momentum.

  • A momentum value is determined for each stock in the SMA50 parent index Universe by combining the stock’s recent 12-month and 6-month price performance. This is the standard implementation of a price momentum value.
  • This momentum value is then risk-adjusted to determine the stock’s Momentum Score.
  • All securities in the SMA50 Universe are weighted by the product of their Momentum Score and their market cap, as follow:

Momentum Weight for SMA-MT  = Momentum Score * Market Capitalization Weight in the SMA50.  Momentum weights are normalized to sum to 100%.

SMA50_MT

SMA-ST: Sentiment Tilt

– Using SMA’s S-Score and SV-Score as factors, emphasize stocks with positive levels of social media sentiment and intensity, while attenuating stocks with low sentiment levels.

  • A composite factor score is determined for each stock in the SMA50 parent index Universe from the linear combination of the stock’s monthly S-Score and monthly SV-Score.
  • This composite factor score is used to determine the stock’s Sentiment Score.
  • All securities in the SMA50 Universe are weighted by the product of their Sentiment Score and their market cap, as follow:

Sentiment Weight for SMA-ST  =  Sentiment Score * Market Capitalization Weight in the SMA-50.  Sentiment weights are normalized to sum to 100%.

SMA50_ST

SMA-SMT: Blended Tilt

–Define a factor which is a combination of sentiment and momentum tilts.

  • A combined factor is determined for each stock in the SMA50 parent index Universe from a linear combination of the stock’s Momentum and Sentiment scores.  Initial results for the blended tilt factor used an equal weighting of Momentum and Sentiment scores.
  • This combine factor score is then standardized and used to determine the stock’s Senti-Momentum Score.
  • All securities in the SMA50 Universe are weighted by the product of their Senti-Momentum Score and their market cap, as follow:

Senti-Momentum Weight for SMA-SMT  =  Senti-Momentum Score * Market Capitalization Weight in the SMA-50.  Senti-Momentum weights are normalized to sum to 100%.

SMA50_Combined

Comparative performance for all four theoretical portfolios is below.

SMA Relative Performance

Overlaying standard benchmark performance you can clearly see the effectiveness of the SMA 50 with various tilt strategies to outperform the benchmarks.

SMA Relative Performance bench

The SMA 50 family of indexes provide a low turnover way to benefit from exposure to social sentiment.  To learn more please contact us at ContactUs@SocialMarketAnalytics.com

Social Market Analytics Now Has Six Years of Out-Of-Sample History!

Social Market Analytics, Inc. (SMA) is celebrating six years of out-of-sample data in US Equities.   This data is unique in that it is a true representation of the Twitter conversation at each historical point-in-time.

Since our launch, SMA has become a leader in providing sentiment data feeds to the financial community.  Our data has become an integral part of our customers investment process.  Our customers are Quantitative Trading Firms, Hedge Funds, Sell Side Brokers, Traders and many others. SMA data is suitable for HFT, Quantitative Trading, Risk, Short Lending, Smart Beta, Fama-French Models, VAR among others.  Predictive signals range from a few minutes to quarterly.

SMA’s analytics generate high-signal data streams based on the intentions of market professionals.  Our patented machine learning process has produced six years of strongly predictive data as illustrated in the chart below.  This chart illustrates the subsequent performance of stocks based on pre-market open (9:10 am Eastern) sentiment scores.  Stocks with high sentiment subsequently out perform as illustrated by the Green line.  Stocks with strong negative sentiment go on to under perform as evidenced by the red line.  The blue line represents a theoretical equally weighted long short portfolio.  The table below illustrates Sharpe and Sortino ratios.

 

Fullhistory

Decile Spreads for Twitter & StockTwits

Today I will explore decile groupings based on S-Scores, and  plot cumulative subsequent returns. We typically focus on an S-Score > 2 for subsequent positive movements in stock prices, and an S-Score < -2 for negative movements in stock price.

Our metrics identify when a conversation becomes significantly more positive or negative than normal.  Most stocks have normal conversations on any given day.  On these days there are other factors driving the security. “Normal” conversation securities will typically follow the market, as you see in the SMA data set.  High sentiment out-performs and low sentiment under-performs,  Open to Close, and Close to Close, across Twitter and StockTwits.

The only filter we add is that the prior day’s closing price must be above $5, to avoid penny stocks.  Total return time series are used for returns, and time series are equal weighted.

The first chart illustrates subsequent Open to Close returns based on S-Score deciles at 9:10 a.m. Eastern time. As you can see, the deciles are in order with top decile securities out-performing and bottom decile securities under-performing.  SPY is represented by the black line and the universe is blue.

Twitter-Pre-Open

Pre-Market Close deciles are below.  S-Scores are taken at 3:40 p.m. Eastern and Close to Close returns are calculated.  Again, high S-Score securities out-perform and low S-Score securities under-perform, with the universe in the middle.

Twitter-Pre-Close-Close

StockTwits is the largest chat community for active traders.  Its users are professional traders discussing long and short positions. The below chart looks at S-Score decile returns based on StockTwits conversations.

Data is consistent across deciles.  A unique characteristic of the StockTwits feed is that there are significant short conversations.  The lowest two deciles have negative returns.  This is a function of the StockTwits community being able to short securities by direct short selling or taking net short options positions.

StockTwits PreOpen

Pre-market close deciles are below.

StockTwits CLose-close

To learn more about Social Market Analytics and the products we offer please visit our website, or contact us here.

Thanks,

Joe

2016 In Review

Last year was a good year for SMA data.  High sentiment securities outperformed and low sentiment securities underperformed with good Sharpe’s and Sortino’s.  The below tables contain returns and Sharpe/Sortino ratios for the full history of Social Market Analytics S-Factor data.   Correlations to standard factors continue to be near zero. I’m sure our data can help in your investment process, contact us to learn more.
Five-year return summary:

returns2016

 Sharpe / Sortino

sharpes

Weekly, Monthly Quarterly Re-balance

As we move into a new year Social Market Analytics (SMA) has acquired five years of out-of-sample data.  This real history has enabled us to build signals for longer holding periods.   In this blog we will explore the use of SMA data for weekly, monthly and quarterly holding periods.

Portfolio managers often re-select securities for their portfolios at set re-balance periods.  These periods can be weekly, monthly quarterly, yearly….  As we accumulate history we are able to create factors with longer term statistical significance.  Longer term for SMA means monthly and quarterly.   For these longer holding period portfolios we created a three factor model using Raw-S, SV-Score and S-Buzz.  These factors look at sentiment, levels of volume relative to normal conversations for that security and relative to the entire universe.   Historical baselines for these securities have been extended to 50 and 200 days.  These three factors are combined into a multi-factor score and the top and bottom stocks are selected for long, short, and a theoretical long/short portfolio.  Returns of these theoretical portfolios are below.

Each portfolio is selected from a universe of the largest 450 stocks that trade options on the CBOE.  SPY is the benchmark in each chart.  As you can see each portfolio significantly outperforms the SPY.  Each chart shows returns.  Monthly and quarterly show the diversification benefit of sentiment data by displaying beta.

Weekly returns with and without transaction cost versus SPY.

weekly

v7

v8

Quarterly Rebalance portfolio.

v9

v10

There is significant predictive power in sentiment data over longer holding periods.  SMA is unique in that we have been collecting this data for five years. Our data is free of survivorship and look ahead bias in the Tweets and universe.

For more information please contact SMA at ContactUs@SocialMarketAnalytics.com