The target of this research was to find an indicator that helps predict the direction of the overall US Equity market for the next week using sentiment data from the previous week. The hypothesis is when there is high volatility in sentiment over the previous week, which means investors have differing opinions, the subsequent week overall market performance will underperform. When volatility on sentiment is low or neutral, the crowd has reached a consensus and the general market will outperform over the next week. The sentiment metric used to represent volatility is Raw-Volatility in SMA’s S-Factor data feed, which captures the volatility of the sentiment from Twitter conversations. All Raw-Volatility data points were taken from the 3:40 pm ET timestamp (20 minutes before the market close). We calculated the summation of Raw-Volatility for each date as a proxy to represent the volatility of Twitter social sentiment on the entire market. The exact calculation is as follows, where “N” is the number of companies with sentiment on that date and “D” is the date:

We then created a 7-day standardized volatility using a 91-day benchmark:

This Z_Volatility score follows a roughly normal distribution.

Using the S&P 500 ETF Trust (SPY) as a proxy of general market performance, we then look at the relationship between Z_Volatility and SPY’s return series. The daily close-to-close return is calculated as:

Hypothesis: When Z_Volatility for the previous closing Date is high, the subsequent market performance will be lower. When Z_Volatility is low or neutral, the next day’s market performance will be higher.

To test this, our strategy is to open short position of SPY when Z_Volatility > 1. When Z_Volatiltiy is =< 1, the portfolio treats SPY as a long position. This hypothetical portfolio is then compared to SPY over the past 10 years:

Prior to the COVID-19 pandemic, which began in early 2020, SPY outperformed the modified portfolio. However, since then the behavior of this factor changed drastically. Here is the same graph as above starting in 2020:

Taking a closer look, the separation since the beginning of 2020 is quite significant. Adding a short position to SPY when volatility on sentiment is high, has enhanced the portfolio’s return. Even though many of the days will maintain a long position, the Z-Volatility is predictive of downturns in the market since 2020. Traders could use this metric as an indicator to stay out of the market, or at the very least trade with more caution. The COVID-19 Pandemic led to a large amount of uncertainty surrounding the stock market and the direction its heading. A high Z_Volatility score indicates the public’s opinion is more uncertain about the direction of various stocks. This research shows the value of sentiment from Social Market Analytics in predicting macro-level events and price movements.

If you are interested in learning more about how SMA’s S-Factor data can help your trading strategies, please email us at or schedule a demo using this link.

At Social Market Analytics we use proprietary techniques to return the most accurate Twitter volume for topics of interest.  First, we use a topic model not just $Ticker.  Most vendors use the CashTag concept to identify securities.  At SMA we believe only using CashTag excludes a lot of valuable conversation.  We return higher volume and cleaner conversations because we use a machine learning rules based system to return all conversations about a security that are not tagged with $Ticker.  In the diagram below we return about 500 extra Tweets a day for Tesla Motors versus just $TSLA.  Our topic model evolves with the conversation over time.

After applying our topic model filter we additionally filter Tweets based on our proprietary account validation metrics.  Only Tweets from our SMA approved accounts are included.  In the below example, there are about 500 Tweets for Tesla Motors from the certified accounts per day.   These accounts pass our multi-step algorithm.  One metric we use is weighted accuracy over time.  For example, when a Twitter account is bullish on a security what percentage of time does that security subsequently move higher.

Below is a visualization of SMA Twitter filtering process for the Tesla topic.

Below is a time series of Tesla Topic model versus $TSLA with the additional filter for SMA certified accounts.

As you can see from the charts SMA’s proprietary technology provides the truest view of the each securities topic model.  To learn more about our technology or receive a sample data set


Social Market Analytics, Inc. (SMA) has been the leading provider of predictive quantitative signal in the alternative data space for 7 years. Over the years, we have developed patented algorithms that use machine learning and natural language processing to provide content that generates alpha. Our NLP is unique because of our proprietary processes that tag sentiment weights based on the language used in finance per asset class. The processing of tweets for futures and commodities is different from what we use for equities.

There have been a lot of conversations around Natural Gas futures in social media lately. Through our partner CME Group , people have been monitoring social sentiment from SMA in real time on their active trader site.

Recently, we did as study on using SMA signals to create a Long Short trading strategy using Natural Gas futures. In the example here, we are using front month futures contract and trading daily using a combination of S-Score (a measure of unusual sentiment) and SV-Score (a measure of unusual twitter volume activity).

The strategy buys contracts when the sentiment (S-Score) is positive. We scale up the long position when the sentiment is positive, and the volume of tweets is also significantly high (SV-Score). Conversely, when the sentiment is negative, we sell contracts and go short. We sell more contracts when sentiment is negative with significantly high number of tweets. For this study, we use a maximum of 100 contracts when going long and 100 contracts when taking short positions.

The sentiment strategy performs significantly better than the Natural gas prices, returning 87.42% YTD. We also avoid the volatility in the price and get a Sharpe of 3.53 on the strategy.


A PnL curve of investment of $300,000 in 100,000 contracts on Jan 1, 2018 is shown in the chart below.

The strategy is profitable throughout the  period, and the maximum drawdown is only 7.19%, which is significantly better than the 29.72% drawdown in the natural gas prices YTD.


Every year Social Market Analytics (SMA) is proud to work with the University of Illinois Masters of Science in Financial Engineering Students on a practicum project. In the past we have explored looking at sentiment to predict the VIX, enhancements to traditional indexes and smart beta ETF’s. This year we decided to tackle the most popular topic of the last year – Bitcoin Trading!   We worked with RCM Capital’s Strategy Studio Platform for back testing to develop a Bitcoin trading strategy combining price momentum with sentiment to keep you in the market when Bitcoin is trading up and minimizing draw downs when Bitcoin retreats as it did in early 2018.

Social Market Analytics tracks sentiment on the top 275 market cap currencies, the below Bitcoin strategy performs similarly on other Crypto currencies.

The students did a wonderful job in strategy construction and explanation.  I will undoubtedly leave something important out. for details.

At it’s core the strategy buys on a price breakout with a sentiment confirmation.  Exit when price breaks down and is confirmed with sentiment.  Buy when the price crosses above (K) standard deviations over a 21 day moving average of price.  Variable K ranged from .5 to 2. Results shown use a .5 standard deviation multiplier.  Strategy visualization is below.


Your first trigger is a breakout above K- Standard deviations of the 21 day moving average.

The confirming signal is based on the Social Market analytics S-Score value.  S-Score is a normalized representation of Bitcoin’s Sentiment time series over a look back period and is updated every minute.  It measures the tone of the conversation on Twitter relative to the benchmark time period.  If Bitcoin is breaking out and the sentiment is 2 standard deviations more positive than normal you initiate or add to your position by 50%.  If the conversation is 1 standard deviation more positive than normal  increase the position 25%.  If the standard deviation price break out is not confirmed by sentiment then no position change.

There was no short position initiated with futures.  Exit criteria are opposite entry criteria.  Price break below K – Standard deviations below a moving average. Confirmation with S-Score.


Dollar P/L results indicated this portfolio successfully navigates the the bitcoin draw down of early 2018.   2018 in isolation is below.


Overall performance with Buy & Hold Bitcoin comparison.


Sharpe ratio and draw down improve dramatically with the momentum and sentiment confirmation.


Again, please for more information on our offerings.

Thanks again to the University of Illinois MSFE students and RCM  Capital Markets for contributing to this project.






Joe Gits, CEO of Social Market Analytics, recently spoke at the 34th annual CBOE Risk Management Conference.

Gits spoke at RMC about SMA’s patented technology, the Social Sentiment Engine, and Twitter’s relevance in financial markets.

Hosted by the Chicago Board Options Exchange, the RMC is an educational forum dedicated to exploring the latest products, trading strategies and tactics used to manage risk exposure and enhance yields. The RMC is the foremost financial industry conference designed for institutional users of equity derivatives and volatility products.


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.


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.


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.



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.




Quarterly Rebalance portfolio.



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