I had the pleasure of moderating a one-hour panel discussion for more than 60 attendees at CBOE on December 16 featuring these three experts: •        Joe Gits, CFA, CEO and Co-Founder - Social Market Analytics (SMA) •        Professor Koleman Strumpf, Professor of Business Economics - University of Kansas School of Business •        Dr. Wachi Bandara, Chief Research Officer – Pluribus Labs

1-panel

The panel discussed a number of topics, including: •        The science behind predictive markets and social media sentiment analysis •        How crowdsourced predictions have performed in forecasting publicly followed events, such as Brexit and the 2016 Presidential election •        Applications for predictive analytic tools to CBOE’s product set •        CBOE’s partnership with SMA to launch sentiment-based strategy benchmark indexes

I began the discussion by noting, for example, that the CBOE /CME FX British Pound Volatility Index (BPVIX) rose 210% in the period from May 2 to June 14 (prior to the June 24 Brexit), and that the VIX® Index rose nine days in a row (from Oct. 25 through Nov. 4, around the time of an FBI announcement on emails by Hillary Clinton). I also noted that CBOE has 727,000 followers at www.twitter.com/CBOE. I then read the quote below (from a Bloomberg News story by Adam Tiouririne on Nov. 16, 2016) and asked the expert panelists how accurate the quote is -- “Polls had her winning. Prediction models had her winning. Financial markets had her winning. But Twitter had Hillary Clinton losing, with a steady downtrend in sentiment that foreshadowed her stunning defeat to Donald Trump on Election Day. The 2016 campaign featured more than 300 million tweets mentioning Clinton or Trump, with the Republican commanding a dominant 2-to-1 share of that conversation. Both candidates faced unprecedented unfavorable ratings among voters, but sentiment on Twitter gave Trump an edge…” Professor Koleman Strumpf discussed polling and prediction markets. While prediction markets (such as Betfair) often forecasted well prior to 2016, the prediction markets generally did not forecast well in 2016 for these three major events: (1) the GOP nomination; (2) Brexit, and (3) the U.S. Presidential election. He also noted that there are more challenges for polling now that many people have cell phones with area codes that no longer reflect where people live.

Dr. Wachi Bandara noted that Pluribus Labs analyzes unique content from a diverse array of unstructured data sources and augments it with advanced quantitative research and analytics to deliver actionable, predictive information. He said the firm’s analytics add value across the investment lifecycle, including idea generation, risk management, portfolio construction and trade execution. Joe Gits said that Social Market Analytics (SMA) was founded to create actionable intelligence from unstructured data. The firm’s patented technology has the ability to harness unstructured yet valuable information embedded in social media streams and provide actionable intelligence in real time to our clients. SMA has become a leader in providing sentiment data feeds to the financial community. In 2016, SMA launched its first of a family of index products in partnership with the CBOE. SMA's analytics generate high signal data streams based on the intentions of professional traders. Our data is unique in that we have four plus years of out-of-sample data which cannot be recreated given a user's ability to delete Tweets at a later time. CBOE-SMA Large-Cap Index (SMLC) The CBOE-SMA Large-Cap Index (SMLC) measures the return of a hypothetical portfolio of 25 stocks with high SMA S-Scores that is rebalanced on a daily basis. The stocks are selected from the CBOE Large-Cap Universe. The CBOE Large-Cap Universe is comprised of stocks that (a) are in the top 15% capitalization tranche of stocks that are the underlying for options listed on the CBOE (approximately 3000) and (b) whose market capitalization is greater than or equal to $10 billion. The CBOE Large-Cap Universe is reconstituted quarterly on the third Friday of the month. At 8:10 am CT, CBOE determines which 25 stocks in the CBOE Large-Cap Universe have the highest SMA S-Scores. It was noted that the SMLC Index had relatively strong performance in 2016; below is a chart from the SMLC fact sheet at www.cboe.com/SMLC

2-smlc-chart