Newsletter Articles


Written by MarketPsych CEO Dr Richard Peterson, our free newsletter provides commentary on current events from a behavioral perspective. Additional topics include behavioral theories and our latest research results.

Subscribe to our mailing list here

We also offer a premium version of the newsletter to our research subscribers, which features additional commentary and trading recommendations.   Find out more here >>


<< Newer articles | Older articles >>


May 02, 2016

Machine Learning, Big Data, and Finding Alpha in the Noise

In quantitative investing, deep learning could be dismissed as a surefire way to overfit on data.  However, as we will describe in more detail below, appropriate set up of deep learning can improve results significantly.  In particular, learning algorithms that first identify the market context in which their strategies are deployed (the regime), are better prepared to learn how markets dynamically adapt to information flow.  Academic research in finance does not yet use deep learning (interdisciplinary research is often slow in coming), but it does support the value of understanding context.  For example, research by Elijah DePalma at Thomson Reuters demonstrates that the performance of common investment strategies differs across market regimes, and these differences may be rooted in the divergent mental states of traders in each context (e.g., optimism in a bull market versus pessimism in a bear market).

Historically, many investors have used the VIX to define market regimes as calm or volatile. As DePalma did in the whitepaper linked to above, sentiment can define market regimes.  Our own data product - the Thomson Reuters MarketPsych Indices (TRMI) - was built to address the problem of dimension reduction in media flow, in part to improve regime detection.  The TRMI quantify and aggregate the information that is directly meaningful and impactful to traders in the form of granular sentiment indexes like "fear" and "joy" as well as macroeconomic indexes like "earningsForecast" and "fundamentalStrength" suggested by a review of the academic literature.   

In the new world of machine-learned strategies, most algorithms use a switching mechanism to change algorithms as regimes shift.  Given that deep learning is based on the neural basis of human decision making, it helps to consider how such human decision making changes depending on the context.  For example, in the midst of market panic, traders think and behave very differently than in the midst of a gradual bull market.  A network that generalizes information like a human mind under stress will behave superiorly during a market panic. However, when markets are quiet, a more complex network architecture can ascertain the nuances of information flow and price behavior. Research supports the use of such regime-dependent approaches in more primitive forms (e.g., switching from value to momentum strategies depending on the VIX level). 

With the recent explosion of such machine-readable and granular data sets, deep learning is better able to show its value.  To support the surge of interest in applying machine learning to vast financial datasets, a new ecosystem - including data such as the TRMI - has arisen.

continue reading...


April 11, 2016

How Fund Managers Trade on Sentiment

Information sometimes hits market prices hard.  The non-farm payrolls number, released the first Friday of each month, has a significant impact on the value of the U.S. Dollar and Treasury bonds.

Elijah DePalma, Senior Quantitative Research Analyst at Thomson Reuters, analyzed the millisecond impact of the nonfarm payrolls (NFP) on the U.S. dollar future contract (DXZ4) on one day—December 5, 2014. A minutely chart of the December dollar index future contract below shows that the price impact is nearly instantaneous with the news release.


SOURCE:  Courtesy of Elijah DePalma, Senior Quantitative Research Analyst at Thomson Reuters

Dr. DePalma notes that on December 5, 2014, $5.7 million of USD contracts (DXZ4) were traded within 63 milliseconds of the NFP release, and $29 million was transacted within 100 milliseconds.

Information that is not numerical (as Nonfarm payrolls is) that is conveyed in text is more difficult to measure.  MarketPsych’s expertise in text analytics allows us to tackle the non-numerical side of information flow – the concepts that influence and bias investors.   Our sentiment-based data feed allows us to deeply understand how information causes herding, and when it doesn’t.  This feed is called the Thomson Reuters MarketPsych Indices, and it is consumed by the world’s largest quant funds and banks for trading and risk applications.

continue reading...


March 06, 2016

The Trump Effect, Media Attention, and Stock Price Patterns

There's no such thing as bad publicity.
~ Associated with P.T. Barnum, the 19th century American showman and circus owner

Before the premiere of her first reality TV show - a show called The Simple Life, set on a farm - Paris Hilton was a little-known American socialite.  Little-known, that is, until someone released an amateur sex tape of her and her then-boyfriend three weeks before the premiere of the show.  

Despite the painful inanity of The Simple Life and the crassness of releasing a sex tape 3 weeks before her show’s premiere, Hilton became a media star and a business success who is now worth around $100 million (per Wikipedia).  

There's nobody in the world like me. I think every decade has an iconic blonde, like Marilyn Monroe or Princess Diana and, right now, I'm that icon.
~ Paris Hilton

Any publicity - even the moral outrage over a (probably deliberate) sex tape release - was good publicity for her brand.   Hilton’s strategy was later repeated by Kim Kardashian and most recently Donald Trump (minus the tape, so far).

If a strategy of grabbing media attention with morally outrageous acts boosts celebrity brands and sways voting patterns, might media attention to companies also boost stock prices? Today’s newsletter looks at the power of attention to drive stock returns.  While celebrities appear to be boosted by publicity - any type of publicity - studying the repeating effects of media attention on stock prices reveals more nuanced but similarly broad patterns over time.  But before diving into that, a quick plug for our book, launching this month!

continue reading...


January 31, 2016

Oil Price Patterns and Investor Reactions

Daniel Plainview (played by Daniel Day Lewis): Are you envious? Do you get envious?
Henry Brands: I don't think so. No.
Daniel Plainview: I have a competition in me. I want no one else to succeed. I hate most people.
Henry Brands: That part of me is gone... working and not succeeding- all my failures has left me... I just don't... care.
~ There Will be Blood (2007)

In general, statistical analysis of price patterns demonstrates the existence of two opposite sentiment-based patterns in financial prices: overreaction (e.g., panic bottoms and blow-off tops) and underreaction (e.g., trends). The concepts of underreaction and overreaction refer not only to patterns of prices but also to the collective investor reactions to information that fuel such patterns.  

As most of our readers are aware, in partnership with Thomson Reuters MarketPsych derives and distributes the Thomson Reuters MarketPsych Indices (TRMI), representing a real-time quantification of emotional and macroeconomic references in the media to 8,000 companies, 52 stock indexes, 32 currencies, 35 commodities, and 130 countries. When the sentiments extracted from such text are statistically analyzed alongside historical price data, insights emerge into how such information moves crowds of investors and prices themselves.  Oil is one of the more sentiment-driven asset, based on our testing.

continue reading...


January 06, 2016

Affluenza, Anger at the Government, and National Renewal

Whether a commitment to lose weight, get organized, or spend less and save more, most New Year’s resolutions have a common theme – they require self-control.  Our 2013 and 2014 January newsletters focused on personal transformation.  The changes working through the global financial system from 2015 to 2016 are broad-based - e.g., a dramatic decline in energy and commodities prices, a sharp rise in the U.S. dollar, and the increasing cost of credit.  Companies, industries, and entire countries are being impacted, but many are still in denial, hoping for a return to the good old days. Formerly-fringe politicians are gaining social support.  2016 promises to be an interesting year, one that will witness the spread of old challenges and the emergence of new ones. 

Today's newsletter explores social frustration, affluenza, underreaction in the S&P 500, and more to the point of behavioral economics, science-based evidence on how to change society for the better.  As usual, it's a long newsletter, and we recommend skipping ahead to sections of interest.

continue reading...


<< Newer articles | Older articles >>