Prediction: The future of the USA stock market

UCLA professor ^ | April 18, 2003 | Didier Sornette

[hripka]

Based on a theory of cooperative herding and imitation working both in bullish as well as in bearish regimes, we have detected the existence of a clear signature of herding in the decay of the US S&P500 index since August 2000 with high statistical significance, in the form of strong log- periodic components.

Please refer to the following paper for a detailed description: D. Sornette and W.-X. Zhou, The US 2000-2002 Market Descent: How Much Longer and Deeper? Quantitative Finance 2 (6), 468-481 (2002) (e-print at http://arXiv.org/abs/cond-mat/0209065).

For a general presentation of the underlying concepts, theory, empirical tests and concrete applications, with a discussion of previous predictions, see Why Stock Market Crash?.

[hripka]

???

[Thane_Banquo]

BS. Weak-form market efficiency: There are no discernible patterns to be found in past trading activity.

[WaveThatFlag]

Can't tell which type of analysis this guy is using. It it goat's blood or is it chicken bones?

[Psycho_Bunny]

A professor of Geophysics in the Department of Earth and Space Sciences Department?

Lololol.

He may very well be right but......lolololol

[Thane_Banquo]

Haha! If you choose your data points and time period properly, you can "find" patterns, even if they don't exist. Example:

"Hmm. I can't find a pattern from 1988 to 1995 using monthly data, so let's try and find a pattern from 1989 to 1994 using hourly data."

[RightWhale]

Statistical herding. What are they talking about? Nobody made me buy that dog of a stock.

[RetiredArmy]

From UCLA. We do not support the war (but the war was over). You decide.

[sirshackleton]

Your mutual fund prospectus has a much better theory: Past performance is no indication of future results.

[zechariah]

Jim Puplava interviewed Professor Sornette back in March.

[z]

[Mr. Bird]

If you could predict market performance based on statistical modeling, university math departments would be empty. All of the professors would be on their yachts.

Everyone may wish to think about that when they listen to an economist, as well....

[isthisnickcool]

OK. OK. I'll fess up! I've been modeling the stockmarket for several years and have built a real-time system using LEVEL II data streams while analyzing every publically traded company in the US. My results and predictions are now available! I'm making providing them here on FreeRepublic first. Click here.

[Osage Orange]

To reply later.............

[tcostell]

Actually, that's what I now do for a living.

(Really.)

[isthisnickcool]

No kidding?

We actaully built something kind of like what I mention above. I guess you would call it a micro-scalper? Didn't work:) But we might fiddle with it again.

[tcostell]

What I actually do is I design high frequency program trading systems. I have a couple that are working now, and I'm working on a new one (in between other stuff, I'm actually trained as an Economist).

[Tauzero]

Very cool.

[Tauzero]

"BS. Weak-form market efficiency: There are no discernible patterns to be found in past trading activity."

Correction: The majority can never discern the patterns in its own behavior.

[bruinbirdman]

A few years ago a derivative fund employed a couple of Nobel economists and their computer program to beat the market. They concentrated on short lived differentials in bond rates and huge leveraging. Seems that they triple and quadruple downed every time they lost. Alan Greenspan thought they were about to ruin the world market system and ordered a bail out.

Long-Term Capital Management.

yitbos

[tcostell]

Their model was sound, they simply employed too much leverage.

What killed LTCM was a combination of arrogance, and Goldman Sachs. The fact that they used quantitative modeling had nothing to do with it.

[gcruse]

How Much Longer and Deeper?

Until it's indecent.

Based on a theory of cooperative herding...

If it's a valid theory, why isn't the professor
the Scion of Wall Street?