Archive for year: 2016

You are here: Home / NEWS / 2016

Social Market Analytics, Inc.

A Leader in Unstructured Financial Data

,

SMA Signals for Monthly & Quarterly Holding Periods

/by

Since our founding in 2012 we have been acquiring out-of-sample history to use in development of factor models.  We now have five years of history, with this history we can create statistically significant signals with monthly and quarterly holding periods.

This blog will explore the use of sentiment data for monthly and quarterly holding periods.  A trading system is explored by looking at exhaustion in social media measured by acceleration and velocity of sentiment as an indicator of price movements.  My next blog will look at traditional monthly and quarterly holding period performance based on a multi-factor sentiment model.

Acceleration and Velocity Trading System

Acceleration and velocity metrics can identify shifting sentiment.   To build these metrics, we created a new 50 period signal in addition to our traditional 20 day signal.  Raw-S is the net sentiment over a 24-hour look back period from a point of observation, derived from Tweets captured during the look back period. By aggregating over 50 periods, we create a 50-period Raw-S we call R50 as follows,

v1

For the purpose of this blog, we use 3:40 PM US Eastern Time factors to create the new metrics. At 3:40 PM US Eastern, a signal is generated near Market Close but with enough time to enter trades and execute at the Close. All trades reported in this paper are assumed to be executed at the Closing price of the day.

The R50 Factor is a raw 50 period sentiment measure.  To normalize the factor, we compute a standardized measure, using the following formula,

v2

where,

S50 is the Z-Score of R50

MA50 (R50) is 50-day moving average of the R50

SD50 (R50) is 50-day moving standard deviation of R50

S50 is a way to represent the R50 raw sentiment estimate on a standard normal curve.

 The New Metrics

We want to identify when the sentiment trend changes direction.  We derive new Velocity and Acceleration metrics from the S50 factor to identify changes in long-term sentiment and the rate of change of long-term sentiment.

We define V50, the velocity, as the one period change in S50,

v3

In our research, the velocity and the rate of change of velocity are equally important in identifying the exhaustion of a sentiment trend.

We call the rate of change of velocity, the acceleration, A50, (the second derivative of the S50),

 v4

Building A Trading Strategy Using Velocity and Acceleration

We observed a mean reverting phenomenon with longer-term sentiment. A high positive peak in the S50 sentiment was typically followed by a decrease in price. Consequently, a local minimum of S50 was followed by price appreciation.

This is the foundation of the trading signals developed.

We used various portfolio sizes to test this trading strategy. Portfolios ranged from 20 highly followed stocks on Twitter to the full SMA equity universe.

Using the metrics defined above, we used the following entry and exit signals,

 

v5

Rational for using these signals is as follows:

  1. A mean reverting relation between S50 and Closing Price.
  2. We want to capture the change and rate of change rather than just the absolute level of sentiment.
  3. A V50 of 0.5 means a change in S50, of 0.5 standard deviations and A50 < 0 is deceleration, A50 > 0 is acceleration.
  4. Due to the mean reverting nature of S50, we wanted to enter when the sentiment was decelerating and had reduced by over 0.5 standard deviations in one day.
  5. We wanted to exit when the sentiment was accelerating and had already increased by 0.5 standard deviations.

 

This was a successful trading strategy across all universes selected.  Below are performance statistics for various universe sets.  20 liquid stock portfolio universe is a universe of stocks that are highly followed on Twitter.  100 liquid stock universe is a universe of 100 stocks that are highly followed on Twitter.  Top 1000 mkt. cap and universe are self-explanatory.

v6

This data is statistically significant, out of sample, and reproducible.  To learn more about the possibilities of sentiment data in your model please contact SMA at ContactUs@SocialMarketAnalytics.com.

Thanks,

Joe

 

/0 Comments/by

SMLC Performance Since Launch

/by

Since SMLC launched six weeks ago there has been a significant increase in volatility.  I thought it would be interesting to see how SMLC has performed during this period of increased volatility.  The chart below shows the cumulative return of SMLC versus the S&P500 over the same period.   Factors derived from the rigorous cleansing and analysis of social media data can provide an edge in the market even during periods of increased volatility.  SMLC is composed of the highest S-Score stocks from the CBOE Large Cap Universe prior to market open.   To learn more about SMLC or the SMA S-Factors please contact Social Market Analytics.  SMLC is up 4.35 percent since inception and the SP is down 1.73 percent over the same period.

smlc

/0 Comments/by

CBOE & SMA Weekly Sentiment Index

/by

As regular SMA blog readers know we recently launched our first index with the CBOE.  The initial index (SMLC) is a daily rebalance portfolio based on the highest sentiment securities in the CBOE large cap universe.  Each morning we build a portfolio of the 25 highest sentiment securities and hold that portfolio to Close.   Back test and live performance have demonstrated the predictive power of sentiment data of a five-year period.

SMA and CBOE researchers have been working on multiple indexes, the next index (SMLCW) is a weekly rebalance portfolio based on the average sentiment of stocks during the week as measure on Friday mornings prior to the Open.  By averaging S-Scores, you generate a longer signal.  The subsequent portfolio is held for a week. The white line is portfolio performance post transaction cost.  As you can see from the chart the impact of transaction cost is minimal.

weeklychart

To learn about SMLCW or how rigoursly defined sentiment factors can help in your investment process please contact us.

Regards,

Joe

/0 Comments/by

CBOE SMA Large Cap Index

/by

On July 29th CBOE and SMA launched the CBOE SMA Large Cap Index (SMLCSM) which tracks the return of a hypothetical portfolio strategy based on Social Market Analytics (SMA) S-Scores.  The SMLC portfolio is an equal pct. weighted portfolio of the 25 highest S-Score stocks in the CBOE Large Cap Universe.  Stocks in the CBOE Large Cap Universe are in the top 15% capitalization tranche of stocks that are the underlying for options listed on the CBOE (approximately 3000) and have a market capitalization greater than or equal to $10 billion.

This is the first in what will be a family of indexes based on combined CBOE and SMA expertise.  The next index will be a weekly rebalanced index based on average S-Score over a lookback period.  Sector, Industry, Market Cap banded, and overlay indexes are likely to follow.

In the three weeks since the index launched I have had a number of inquiries as to performance.  It has performed as expected from the back test.  It has outperformed the SP500 over this time period.  SMLC return is represented by the green line, SP500 is represented by the black line.  We would be happy to design custom indexes. Please contact us with any questions: contactus@socialmarketanalytics.com

SMLC

Regards,

Joe Gits

/0 Comments/by
, , , , , ,

SMA Predicts Brexit Two Weeks Before The Vote

/by

People seem surprised that Britain voted to exit the EU.  We at SMA with our partners the CBOE are not nearly as surprised as everyone else.  Russell Rhoads from the CBOE has been blogging and Tweeting with SMA data for two weeks that it looks like the Brexit is going to happen.  Let’s look at the timeline.  Again, this is not a post analysis, these Tweets were out there 2 weeks ago!

Brexit Post on June 8, 2016:

Russell Rhoads, from CBOE wrote a blog about Brexit using the using SSE, the results indicated that an Exit is going to be the result of the vote.

Brexit1

The update from our partners at CBOE talked about the huge increase in Twitter volume about #brexit. One of the key observations was the #VoteLeave campaign had gained far more popularity than the remain campaign. To everyone who was looking, Twitter had shown the signs of a British Exit.

Brexit2

The final post on June 22 talked about strong social media indicators towards the exit. The #VoteLeave campaign has dwarfed the conversations of every other opinion, including the BBC debate. The prediction turned out to be true.

Brexit3

Twitter is the premier leading source of information and SMA can help you make sense of it.  Please contact SMA for more information at contactus@socialmarketanalytics.com

/2 Comments/by
, ,

That’s Two Takeovers in a Week!

/by

Social media beats the mainstream media on a regular basis.  Last week social media beat the news wire in reporting the MSFT acquisition of LNKD (blog post below) and Tuesday Twitter broke SCTY being acquired by TSLA.  This information is not theoretical – it is actionable data in our feed!

Tesla Motors lit up Twitter, yesterday, when CEO, Elon Musk came out and said their cars can float on water.  Tuesday June 21, the electric car manufacturer took everyone by surprise when they announced their decision to buy the solar panel company SolarCity (SCTY) minutes after the markets closed. The first news article to mention this came out at 4:18 PM CDT. Twitter had already gotten wind of this development 8 minutes prior with a tweet from the account “TopstepTrader”.

TSLA -SCTY

The tweet from “TopstepTrader” was deemed to be credible by Social Market Analytics’ sophisticated algorithm, which separates signal from noise to create actionable intelligence. The sentiment started to move in a positive direction the very next minute. By 16:12 CDT, SMA’s subscribers received ‘S-DeltaTM’ alerts on SCTY. The PredictiveSignalTM from SMA became positive at 16:13 CDT and at 16:18, when the first news article came out, the sentiment had already reached an extremely positive level, with Tweet volume soaring high; as was the stock price. Traders who incorporated social media sentiment from SMA into their trading models were ahead of the curve, making profits as the rest of the market was just learning of the news.

SCTY

The S-Delta metric also flagged this move.  The below chart illustrates the delta values for SCTY.  Delta represents the change in S-Score over a 15 minute lookback.  Delta values of 2 or higher are huge outliers. An SMA alarm based on Delta or S-Score would have provided an alert to this breaking news.

SCTY_Delta

To find out how you can use SMA S-Factors in your investment process contact us at Info@SocialMarketAnalytics.com

 

 

/0 Comments/by
, , , ,

Twitter Leads News For MSFT, LNKD Acquisition

/by

As is the case with most corporate events now, MSFT buying LNKD broke on Twitter first. The very first mention of this is any news article was at 7:38 AM (CDT) but Social Market Analytics (SMA) detected this 7 minutes ahead at 7:31. SMA’s patented algorithm digests, filters and evaluates Tweets in real time. The filtering process, a proprietary Tweet account filtering technology built by SMA, separates signal from noise by continuously scanning for accounts that are deemed credible to be included in the calculation process. The tweets from spam accounts are filtered right away.

The following are the 5 tweets that SMA received from these credible accounts in a matter of 13 seconds. All of them pointing towards the same positive news.

Tweets

The 7:32 AM sentiment, as a result, had already started moving positive. By the next minute, at 7:33 AM the sentiment was already positive and soaring up. By the time other news sources caught up to this news, at 7:38 AM, the sentiment was already very positive. The S-DeltaTM alerts which measures the 15 minute changes in the sentiment had started firing up at 7:33 AM as people took notice of this and the Tweet volume kept soaring.

SentimentVisuals

Contact SMA for more information about using Twitter based metrics in your investment process: info@SocialMarketAnalytics.com

 

 

 

/0 Comments/by

StockTwits based S-Factor Return Charts

/by

Social Market Analytics (SMA) aggregates the intentions of  investors as expressed on the StockTwits platform.   SMA creates proprietary S-Factor metrics that quantitatively describe the current conversation relative to historical benchmarks.  This data provides strong predictors of future price movement.  This blog will focus on the deterministic nature of the StockTwits data set when aggregated into SMA S-Factors.    StockTwits is a community for active traders to share ideas enabling you to tap into the pulse of the market:  http://stocktwits.com/

The charts and tables below illustrate the subsequent open to close return of stocks that are being spoken about abnormally positively or abnormally negatively on StockTwits twenty minutes prior to market open.  Sharpe and Sortino ratios for the theoretical portfolios are included as well.  The SMA S-Score looks at the current conversation relative to historical benchmarks and creates effectively a Z-Score.

The Green line below is an index of subsequent open to close return of stocks with abnormally positive conversations on StockTwits prior to the market open.  The Red line is an index of the subsequent open to close return of stocks with an abnormally negative conversation prior to market open.  The black line represents the market open to close return and the blue line represents a theoretical long/short portfolio.

These charts clearly illustrate the predictive information present in the StockTwits message stream. If there was no predictive power in the StockTwits data set the Green, Red, and Black lines would be nearly identical -statistically not the case.  These signals are available at 9:10 am Eastern time well before the market open.

The chart below looks at the full SMA history of StockTwits based S-Factors.  The theoretical long portfolio has a Sharpe Ratio of 1.53, theoretical short portfolio -.82 Sharpe and LS portfolio has a Sharpe of 3.68.   Sortino Ratios are above one as well.  There is strong predictive power in this data.

FullHistoryStockTwits

The last year has been particularly challenging for the Hedge Fund community.  Below is a chart with the performance of the theoretical portfolios broken out from 1/1/2015 to current.  As you can see these portfolios performed well in this volatile market period.

LastYearStockTwits

For more information on these data sets please contact Pierce Crosby:  (pierce@stocktwits.com)  or Joe Gits: (joeg@socialmarketanalytics.com)

Regards,

Joe

/2 Comments/by
, , ,

Twitter Sentiment and Longer Holding Periods

/by

Signals derived from Twitter data have typically been viewed as shorter term signals.  There are a number of reasons for this.  One reason is the lack of out of sample data to back test trading systems on.  At SMA we now have nearly four and a half years of sentiment metrics to use in the creation of longer term signals.  Long-Term is a subjective term when discussing holding periods.  For our purposes we will be looking at trading signals that generate an average holding period of one month to three months.

At SMA we do not believe that one metric provides the full tone and context of a Twitter conversation.  That is why we publish a family of metrics call S-Factors that provide a richer view of the conversation than what is available with a single metric.

With history we have been able to look at longer term metrics and changes in security prices over longer periods.  We looked at large rapid negative changes in sentiment and determined that these sentiment movements are overreactions and lead to buying opportunities. We introduce two new metrics: Velocity and Acceleration.  The universes for these back test range from 20 large Twitter followed liquid stocks to the entire equity universe.  As you can see below these strategies identify solid buying opportunities and generate healthy average profit per share.  Please contact SMA to learn more about using sentiment to generate longer holding period trading signals with sentiment data.

Below are equity curves and trading statistics net of commissions with various universes. Overall you generate much fewer trades and hold them for longer periods of time.  The 50-day S-Score chart uses the SMA S-Score, Velocity and Acceleration Metrics.  You see that the holding periods are much longer than signals typically generated by social media.  The columns represent different universe sizes.

Slide1

200 Day S-Scores returns are below.  Again, please contact SMA for more detailed information.  Slide2

To learn more please contact us at: ContactUs@SocialMarketAnalytics.com

/0 Comments/by

Bernie Sanders Landslide Twitter Victory

/by

In politics as in equity trading, you bet on momentum.  So the real story coming out of Iowa last night wasn’t Hillary’s razor thin victory or Donald’s fall from grace (foreshadowed in last weeks blog).  I predict that Bernie Sanders and Marco Rubio will steal the headlines in New Hampshire and South Carolina.  I’m no political pundit.  I analyze social sentiment data for a living and my data says you can bet on Sanders and Rubio to surge while Hillary and Donald will continue struggle.  Bernie Sanders won a social media landslide in Iowa, which was indicative of his closing the gap to a virtual tie with Hillary among voters.

Social sentiment is highly predictive of behavior.  We see it in the equities market every day.  People who post their intent are much more likely to act on it.  You could see momentum building for both Sanders and Rubio in the days before the caucus simply by what people were posting about them.  Bernie Sanders won Iowa in a landslide and captured momentum heading into New Hampshire and South Carolina.  He won by nearly 5 times his next closest competitor Marco Rubio who was also a sentiment winner.

With our proprietary S-Factors we can rank regardless of party.  Let’s look at the rank order based on Twitter Buzz – our proprietary S-Score.  This ranking looks at the 24 hour Twitter conversation relative to the prior 20 day Twitter conversation for each candidate.  It’s answering the question:  Who received the biggest boost from Iowa and who was hurt the most?  Any negative value means the current buzz is more negative than normal and the significance of the number indicates how negative.  For example:  The Carly Fiorina conversation is 1.63 standard deviations more negative than normal.

  • Bernie Sanders: 3.91 standard deviations than normal.  The current conversation is more positive than 99.7% of the prior conversations
  • Marco Rubio: 0.689
  • Ted Cruz: 0.656
  • Donald Trump: -0.25 (conversation is more negative than normal, no bounce at all)
  • Jeb Bush: -0.65
  • Ben Carson: -1.08 (current conversation is more negative than 68% of prior conversations)
  • Hillary Clinton: -1.20
  • Carly Fiorina: -1.63

By ranking based on SMA proprietary metrics you can see that Bernie is clearly separating himself from the pack.  He is located in the far upper right corner clearly distancing himself.   Donald Trump is smack in the middle.   In the chart below you get a clear picture of Bernie’s Landslide Sentiment Victory, which as sentiment predictability goes, suggests that he will continue to be a tough opponent for Hillary.

SentimentWinner

To learn more about SMA capabilities contact us at: ContactUs@SocialMarketAnalytics.com

Thanks,

Joe

/0 Comments/by