Archive for year: 2018

You are here: Home / NEWS / 2018

Social Market Analytics, Inc.

A Leader in Unstructured Financial Data

, , ,

Extreme Positive Gold Sentiment on CME Active Trader Website.

/by

Social Market Analytics (SMA) data is live on the CME Active Trader Website.  Real-time sentiment and indicative Twitter volume is used by traders to generate new ideas.  Sentiment data is predictive across various time frames.  High sentiment commodities go on to outperform and negative sentiment commodities underperform.  SMA covers 36 commodities on the CME website for: Agricultural, Equity Indexes, Energy, Metals, Interest Rates & FX.

On Monday 9/24 Gold Sentiment crossed through extreme positive at 7:30 am central time.    https://activetrader.cmegroup.com/Products/Metals

GoldBlog1

Clicking on the chart expands the time frame for further analysis.

GoldBlog2

To learn more about Social Market analytics commodity sentiment data or more about the CME implementation: ContactUs@SocialMarketAnaltics.com.

To receive alerts like this in real time follow us on Twitter at @sma_alpha.

/0 Comments/by
, , , ,

Social Market Analytics Sentiment Data for Forex Trading

/by

Social Market Analytics (SMA)  provides real-time sentiment data for equities (North America & LSE), commodities, foreign exchange, Crypto Currencies and ETF’s.

In this blog I am going to explore a trading system using the SMA Twitter based sentiment data to trade a basket of: EURUSD, EURGBP, GBPJPY, GBPUSD ,USDCAD ,USDCHF ,USDJPY.

We will explore two straight forward trading systems:

  • Forex Sentiment RSI: Daily Long/Short Strategy
  • SMA S-Score Based Currency Selection Model

RSI Calculation Methodology 

CurrencyBlog 1

This strategy is a single-factor model solely based on adjusting daily weights according to 3-Day Sentiment RSI on the 7 of the highest daily volume Forex pairs. It is long-short with the assumption that tails act with similar magnitude.

  • Long/Short
    1. RSI >= 50, Long
    2. RSI < 50, Short
  • 50% Long & 50% Short Asset Allocation
    1. Long weights are calculated using only longs
    2. Short weights are calculated using only shorts
  • Daily weight adjusted following:
    1. separately for the long side and the short side

 

currencyBlog2

The strategy significantly improves returns compared to an equal weighted baseline.  Sharpe and Sortino ratios are statistically significant:

  • Sharpe Ratio:
    • 2.77 Jan 03, 2017 to July 19, 2018
    • 3.40 YTD
  • Sortino Ratio:
    • 5.40 Jan 03, 2017 to July 19, 2018
    • 7.46 YTD

The volatility of each leg of the strategy is either kept stable or decreased in comparison with the baseline.

SMA S-Score Based Currency Selection Model

This daily trading strategy is based on the S-Score at 09:10:00 EST and executing a 24-hour hold based on these values at 09:15:00 EST. We find consistency across execution times.  The goal is to assess sentiment and take make a directional trade in agreeance, given that the sentiment falls at least 1 standard deviation from the 20-day mean.

Equal weighted based on standard deviation criteria:

– Long: S-Score > 1

– Short: S-Score < -1

– Baseline: Equal Weighted Portfolio of the 7 Currency pair

Long and short legs are capped at 50% of the daily portfolio, even on the occurrence of an outlier day where all pairs are long, or all pairs are short.

currencyBlog3

 

The strategy drastically improves returns compared an equal weighted baseline.  Up to 40% cumulative over a 19-month period with a consistent annual rate of return.

  • Sharpe Ratio:
    • 2.56 Jan 03, 2017 to July 19, 2018
    • 3.56 YTD
  • Sortino Ratio:
    • 4.93 Jan 03, 2017 to July 19, 2018
    • 7.72 YTD

These are straight forward strategies that illustrate the predictive nature of our dataset.  Twitter and StockTwits based factors.  To learn more about how Social Market Analytics sentiment data can help your trading please contact us at contactus@Socialmarketanalytics.com or Doug Hopkins @ (312) 788-2621.

 

/1 Comment/by

Social Market Analytics Sentiment now on CME Active Traders Site.

/by

Over the past several years, social media sources like Twitter are being used more frequently to distribute company news, information, and analysis of Futures and Options. There are 800 Million Tweets a day across the globe. Social media often raises awareness of news and information more quickly than traditional news sources.
Social Market Analytics is excited to announce a partnership with the CME to provide real-time Twitter based sentiment for their active trader website:

https://activetrader.cmegroup.com/Products/EquityIndex?s=EP

SPEmini

This website enhancement allows commodity traders instant real-time access to Twitter based sentiment metrics summarizing the opinions/intentions of professional investors and the number of Tweets from these professional investors. Charts can be expanded by clicking to show different time periods.

SPEminislide2
There are two fields – S-Score and S-Volume.  S-Score is a normalized representation of social media sentiment over a 20-day look back period. S-Score measures the deviation of changes in sentiment intensity of a given commodity and answers the question, “Is the conversation on Twitter about a particular commodity significantly more positive or negative than normal?” Higher levels of sentiment indicate a stronger reaction. High positive sentiment indicates a commodity is statistically likely to move higher. High negative sentiment indicates a commodity is statistically likely to go lower.  SMA’s normalization and scoring process calculates the S-Score for each commodity with active conversations. S-Scores range from -4.25 to 4.25. S-Score above +2.0 or below -2.0 are extreme positive and extreme negative. Scores between 0 and 1 or 0 and -1 are neutral. Volume represents the number of indicative Tweets used in the calculation of sentiment. These are forward looking Tweets from SMA certified professional investors.

 

 

/0 Comments/by

A Returns Analysis on StockTwits Sentiment Metrics

/by

This paper discusses the analysis of a Returns Study done on US Equities using social media sentiment factors from Social Market Analytics (SMA) in a single factor trading model environment. In a comparison to a market reference on a long only strategy, the results indicate an outperformance in returns for positive sentiment stocks and an underperformance for negative sentiment stocks. The long short strategy outperforms the market reference consistently over multiple testing periods.

/0 Comments/by

Application Of Sentiment Analytics To Fama-French Model

/by

In this paper we expand on the Liew (2016) paper exploring the predictive power of StockTwits based sentiment data. We postulate that using a fine grain text analytics approach on social media posts is a better representative of the sentiment factor. This new model shows improvement in both Fama French 5 Factor Model and the Liew paper.

/0 Comments/by
, , ,

UIUC Bitcoin Trading System Practicum Presentation

/by

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.  ContactUs@SocialMarketAnalytics.com 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.

BitcoinStrategyVisual

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.

BitcoinResults

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

Bitcoin-2018

Overall performance with Buy & Hold Bitcoin comparison.

BitcoinStats.png

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

stats2

Again, please ContactUs@SocialMarketAnalytics.com for more information on our offerings.

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

Regards,

Joe

 

 

 

/0 Comments/by
, , , , , , , ,

Introducing the Social Market Analytics (SMA) 50 Long Index

/by

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

/0 Comments/by

Social Market Analytics – Year in Review

/by

At Social Market Analytics we are continuously reviewing our dictionaries and account rating algorithms.  Year End is a great time to aggregate and publish performance metrics – 2017 was a great year for Social Market Analytics data.  We look at our data in many different ways.  The below tables illustrate the Open to Close performance of securities with statistically significant sentiment scores prior to market open.  Comparison S&P 500 value is open to close as well.  Securities with an S-Score > 2 ( S-Score >2 means the current conversation is much more positive than recent prior conversations)  had cumulative subsequent performance of 25.78% versus the S&P of 6.28.  Stocks with an S-Score < -2 had cumulative negative performance (positive Alpha) of -19.48.  Stocks with positive S-Scores went on to significantly outperform and stocks with negative S-Scores went on to significantly under perform.   2017 was our best year for long short performance.

AnnualReturns2017

Sharpe Ratios for these theoretical portfolios are below.   2017 had the best long/short Sharpe Ratio versus history (6.56), Short (-2.15) & the second best long (2.60)

AnnualSharps2017

The question to ask is why has performance improved over our six years of history?  At SMA we vigorously scrub the Twitter hose to aggregate the intentions of professional investors.  Historical data has provided a deep set for training and cleansing.  First, we identify who we believe are professional investors.  The universe of our certified investors has grown over history – A larger set of inputs.  The number of Tweets related to securities and products has increased – better inputs. Our dictionary has evolved and grown over time.  More inputs, better inputs and better parsing has resulted in more predictive power!  To learn more please reach out to us and I wish everyone a health and prosperous 2018.

Regards,

Joe

 

/0 Comments/by