|By Chuck Thompson, originally published in the August 2011 Socionomist|
A team of researchers in Europe used the Elliott wave model as a basis to forecast the daily net direction of a stock.
During a 400-trading-day test period, they achieved an overall return of 6.8% while the stock lost more than 60%. The authors discuss their findings in “Elliott Wave Theory and Neuro-Fuzzy Systems, in Stock Market Prediction: The WASP System” in the August 2011 issue of the journal, Expert Systems With Applications. The paper’s lead author, George S. Atsalakis, is affiliated with the Department of Production Engineering and Management at the Technical University of Crete. He and fellow authors Emmanouel M. Dimitrakakis and Constantinos D. Zopounidis tested their WASP (Wave Analysis Stock Prediction) system on the stock of the National Bank of Greece from April 11, 2007 to November 14, 2008.
In Search of Third Waves
In their paper’s abstract, the authors write, “[The Elliott wave] theory has been found to be extremely useful and accurate, particularly in problems of forecasting.” 1 The researchers say the greatest challenge in their study was to “count the waves, and spot the current position of the market or stock on an Elliott wave pattern.” Because of their belief that third waves should be the easiest to track—due to their “length, power, and speed”—they focused their forecasts on these waves.
They argued that during third waves up, a shorter moving average of prices should be significantly higher than a longer one. Therefore, they subtracted a 35-day average from a 5-day average to produce an Elliott wave oscillator (EWO). They note that the EWO will have:
- higher values during third waves up,
- lower but still-positive values during the first and fifth waves up, and
- negative values during the biggest corrections or downtrend impulse waves.
How the WASP System Developed
The three researchers begin their 11-page paper with a discussion of the basis for the WASP system, including Elliott wave theory, the Fibonacci sequence and the benefits of fuzzy logic.
The researchers note that fuzzy logic is well-suited for stock market forecasting, a problem in which “information is not noise-free.” The primary weakness of systems using fuzzy logic, however, is that they require predefined knowledge. Users must set all membership functions in advance. By contrast, neural networks, a computational method of modeling data, have the “ability to learn by example, in other words to create knowledge from past data. Additionally, such networks are … extremely useful in pattern recognition.”1 But neural networks also have a weakness: They provide inadequate information about the impact of every input on the output. They also require high computational power, which limits the number of input variables.
To compensate for the respective weaknesses of fuzzy systems and neural networks, Atsalakis and team used a neuro-fuzzy system, which is basically a neural network that transforms the inputs into a fuzzy set. The WASP system is based on a neuro-fuzzy architecture called ANFIS, which is “extremely efficient in forecasting time series,” the authors say.
WASP did not utilize a single mathematical model but nine different models, because different models provided good results at different times. Thus, the system generated nine different forecasts for the next day, and the average of those nine forecasts became the final forecast.
The system also produced a “hit rate,” which is the number of times that it made a correct forecast divided by the total number of attempts. And it produced a “confidence index” based on the percentage of the nine models that agreed with the system’s overall forecast.
The WASP System at Work
Using a paper portfolio of 10,000 euros, Atsalakis and team tested WASP on the stock of the National Bank of Greece. They bought when the forecast was positive and closed the position when the forecast became negative. During the 400-day research period, the WASP System made 63 stock transactions. The researchers divided the testing period into three sub-periods, the last of which included the 2008 financial crisis. For each sub-period, the team compared the WASP system’s return to that of a buy-and-hold strategy. The three sub-periods and their results were as follows:
- April 11, 2007 to January 23, 2008—WASP return, +17.73, buy-and-hold return, -9.57; hit rate, 61%;
- January 24, 2008 to June 25, 2008—WASP return, +19.65, buy-and-hold return, -19.39; hit rate, 60%;
- June 26, 2008 to November 14, 2008—WASP return, -24.28, buy-and-hold return, -46.35; hit rate, 60% at the beginning and 53% at the end.
For the entire 400-day period, the WASP system achieved a hit rate of 58.75% and accumulated an overall 6.79% gain versus a 60.9% loss for the buy-and-hold strategy.
Our Assessment of the Results
The paper is published in a journal with a good impact factor (a measure of the average number of citations to papers appearing in the journal during a survey period). As a result, it has the potential to interest a sizable number of readers in a deeper investigation of the Elliott wave model and its value in understanding the markets.
Having said that, momentum measures—including a quantitatively fixed dual oscillator such as the 5-day/35-day oscillator that the researchers used—can capture only a small part of the Elliott model. Oscillators do not express the fractal nature of the markets but pertain to only one or two degrees of trend. They serve best to confirm or challenge a wave interpretation. We suggest that in order to properly identify any waves, including third waves, it is necessary to first apply Elliott’s rules and guidelines.
On a theoretical note, the researchers express their belief that Elliott waves unfold due to investors’ conscious reaction to changing prices. Socionomics, however, argues emphatically that Elliott wave patterns unfold due to unconscious changes in social mood.
We commend the researchers for the lengths to which they went to design a careful statistical study. We are encouraged by their attempts, as well as others’, which together are confirming the utility and validity of the Elliott wave model, and of technical analysis in general, as a tool for analyzing and understanding the markets.■
1Atsalakis, G.S., Dimitrakakis, E.M., Zopounidis, C.D. (2011, August). Elliott wave theory and neuro-fuzzy systems in stock market prediction: The WASP system. Expert Systems With Applications, 38(8), 9196-9206.
Socionomist is a monthly online magazine designed to help
readers see and capitalize on the waves of social mood that contantly occur
throughout the world. It is published by the Socionomics
Institute, Robert R. Prechter, president; Matt Lampert, editor-in-chief;
Alyssa Hayden, editor; Alan Hall and Chuck Thompson, staff writers; Dave Allman
and Pete Kendall, editorial direction; Chuck Thompson, production; Ben Hall,
For subscription matters, contact Customer Care: Call 770-536-0309 (internationally) or 800-336-1618 (within the U.S.). Or email firstname.lastname@example.org.
We are always interested in guest submissions. Please email manuscripts and proposals to Chuck Thompson via email@example.com. Mailing address: P.O. Box 1618, Gainesville, Georgia, 30503, U.S.A. Phone 770-536-0309. Please consult the submission guidelines located at http://www.socionomics.net/PDF/Socionomist_Submission_Guidelines.pdf.
For our latest offerings: Visit our website, www.socionomics.net, listing BOOKS, DVDs and more.
Correspondence is welcome, but volume of mail often precludes a reply. Whether it is a general inquiry, socionomics commentary or a research idea, you can email us at firstname.lastname@example.org.
Most economists, historians and sociologists
presume that events determine society’s mood. But socionomics hypothesizes
the opposite: that social mood regulates the character of social events. The
events of history—such as investment booms and busts, political events,
macroeconomic trends and even peace and war—are the products of a naturally
occurring pattern of social-mood fluctuation. Such events, therefore, are not
randomly distributed, as is commonly believed, but are in fact probabilistically
predictable. Socionomics also posits that the stock market is the best available
meter of a society’s aggregate mood, that news is irrelevant to social
mood, and that financial and economic decision-making are fundamentally different
in that financial decisions are motivated by the herding impulse while economic
choices are guided by supply and demand. For more information about socionomic
theory, see (1) the text, The
Wave Principle of Human Social Behavior © 1999, by Robert Prechter;
(2) the introductory documentary History's
Hidden Engine; (3) the video Toward
a New Science of Social Prediction, Prechter’s 2004 speech before
the London School of Economics in which he presents evidence to support his
socionomic hypothesis; and (4) the Socionomics Institute’s website, www.socionomics.net.
At no time will the Socionomics Institute make specific recommendations about
a course of action for any specific person, and at no time may a reader, caller
or viewer be justified in inferring that any such advice is intended.
All contents copyright © 2021 Socionomics Institute. All rights reserved. Feel free to quote, cite or review, giving full credit. Typos and other such errors may be corrected after initial posting.