I can prove "Random walk theory" wrong

[Trembling Hand]

I am not endorsing any product, website, black box or other commercial fluff, just the research, I can prove the results are 100% accurate.
I am flattered by skepticism.
I am happy if the thread ends here.
Thank you.

What a classic!! You have found the golden goose sitting on the holy grail and you want to "prove" it to a bunch of dudes on a forum

Nick off and make your millions. Come back and tell us I told you so when you have some real proof.

 

[Stormin_Norman]

its random walk hypothesis. it is not a theory.

i think lo and macKinlay will be mighty pissed youve beaten them to their conclusion that the random walk hypothesis is bogus.

 

[Pager]

Im all for giving people the benefit of the doubt but this thread with a different user name was on a US forum today as well, are you CTS01 on elite trader ?, http://www.elitetrader.com/

Here's a post from that thread.

"This exact same thread appears at least once a month. Always with a new thread starter.

Are all of you the same person?

Have you ever succeeded in selling one of your systems here?"

If you have nothing to sell but just want to prove/share your ideas then IMO, go ahead but could you at least make that clear

 

[DMC31]

I am not selling anything here, I was after just after some feedback on it, (predicting stock market direction, definitely can be done)
If I went to a brokerage, would they take me seriously, probably not, unless I could prove the results, which I can, and then they would steal it.

So I will keep on trading it, and keep it to myself, for another four years.

Thank you for posting.

 

[Pager]

I am not selling anything here, I was after just after some feedback on it, (predicting stock market direction, definitely can be done)
If I went to a brokerage, would they take me seriously, probably not, unless I could prove the results, which I can, and then they would steal it.

So I will keep on trading it, and keep it to myself, for another four years.

Thank you for posting.

Well go for it DCM31 , think many would be interested but don't think you can blame people for being sceptical that you arnt here ultimately on some kind of sales pitch.

 

[beamstas]

Guys... give some respect......

In his "another four years" he'll be sitting along side bill gates and buffet..

 

[pilbara]

We contacted Google finance last week with a proposal, to prove our research, and are waiting for a reply.

do you know how Google Finance was started? At Google each employee can spend 20 percent of their time on personal projects, working on things they are interested in. This is how Google Finance was started, by two engineers working alone on their project. Once they had something to show, they pitched the idea to the Google senior management Sergey Brin and Larry Page, who decided to back the idea and put huge resources of the company behind it. Google has a huge number of potential projects from their own employees, so they are unlikely to follow up something from outsiders. Google seek to own intellectual property so it's not worth sharing it with them.

Instead just keep trading your system, and build up a history of real trades with your own capital. Once you have a good history, approach a prop shop with your trading statements, and try to convince them it is worth backing you with their capital.

 

[Agentm]

I am not selling anything here, I was after just after some feedback on it, (predicting stock market direction, definitely can be done)
If I went to a brokerage, would they take me seriously, probably not, unless I could prove the results, which I can, and then they would steal it.

So I will keep on trading it, and keep it to myself, for another four years.

Thank you for posting.

anyone with a formula like that would never disclose it to anyone dmc31. you would simply use it and pass it on to your children and then on and on.. and live like a king..

you asked for marketing advice, yet you dont disclose what you offer in return for it..

you want to discuss something you cant prove in fear of revealing the formula..

i have found the lost city of gold, el dorado, and i cant seem to discuss it with anyone either, so we both have the same problem..

i tell you what,, i will swap you my knowledge on el dorado for your knowledge on taking random walks.. sound fair?

 

[James Austin]

I am not selling anything here, I was after just after some feedback on it, (predicting stock market direction, definitely can be done)
If I went to a brokerage, would they take me seriously, probably not, unless I could prove the results, which I can, and then they would steal it.

So I will keep on trading it, and keep it to myself, for another four years.

Thank you for posting.

DMC31

would you like to add substance to the thread??


if yes,

[1] post all trades, dates, entries, exits, stops, stock codes, P/L etc,
which you claim follow your "predictive" system.

[2] substantiate these trades with "actual" broker statements for all to view

this is the most direct way to get people to take you seriously

will you do this DCM31?

i think it is fair that if you chose not to substantiate your claims then we can all assume . . . . well you know

i await your speedy reply

 

[Timmy]

FFS...

TH shows the random walk hypothesis is wrong every frikkin’ day.

 

[nizar]

[2] substantiate these trades with "actual" broker statements for all to view

He doesnt need actual broker statements to verify his claims.
If he just posts realtime, then anybody can verify them.

 

[pilbara]

Didn't Benoit Mandelbrot already find rather persausive evidence against random walk using cotton data in the 1960s?

I looked up a book review of Mandelbrot's "The Misbehaviour of Markets", and it sounds convincing:

The author renders a brilliant critique of modern finance theory. He criticizes all its components, including CAPM, the Efficient Market Hypothesis, and the Black Scholes model as being flawed. All these theories rely on two main assumptions. The first one is that market prices are normally distributed. The author, using price charts, demonstrates that market prices do not follow a normal distribution; but instead a Cauchy distribution. Such a distribution is associated with fatter tails. This means that catastrophic drop in market prices happen more frequently than a normal distribution suggests. The second assumption of modern finance is that market prices are independent of each other. Yesterday's prices have no influence on today's. The author makes a case that even if prices are not correlated, their volatility is correlated over time. Thus, big price swings tend to cluster. If a stock moved by 10% yesterday, it is likely it will move by an above average amount today even if we don't know the direction of that change. He calls this correlation of volatility (instead of price) long-term dependence.

 

[nizar]

Mandelbrot's "The Misbehaviour of Markets"

Doc or others,
Is this a good read?

 

[doctorj]

If you enjoyed Taleb, it's worth the read.

 

[Stormin_Norman]

there seems to be a lot of misconception about what random walk hypothesis actually is.

Malkiel argues that asset prices typically exhibit signs of random walk and that one can not consistently outperform market averages.

http://en.wikipedia.org/wiki/A_Random_Walk_Down_Wall_Street

 

[doctorj]

there seems to be a lot of misconception about what random walk hypothesis actually is.

Random walk existed long before Malkiel. This wikipedia article is probably more helpful...

 

[Stormin_Norman]

it comes from the markov process. i was not arguing that book created a statistical idea; but it was the first to gain widespread attention in the economics field.

A Markov process, is a mathematical model for the random evolution of a memoryless system, that is, one for which the likelihood of a given future state, at any given moment, depends only on its present state, and not on any past states.

i did quite a bit of study into random walk/markov processes during my economics degree.

my point was merely that some of the discussion misrepresents what random walk is attempting to explain what is statistically observed.

it is summed up in the 'past performance is not indicative of future results'.

to take it out of the financial context :

The random walk hypothesis was also applied to NBA basketball. Psychologists made a detailed study of every shot the Philadelphia 76ers made over one and a half seasons of basketball. The psychologists found no positive correlation between the previous shots and the outcomes of the shots afterwards. Economists and believers in the random walk hypothesis apply this to the stock market. The actual lack of correlation of past and present can be easily seen. If a stock goes up one day, no stock market participant can accurately predict that it will rise again the next. Just as a basketball player with the “hot hand” can miss his or her next shot, the stock that seems to be on the rise can fall at any time, making it completely random.

http://en.wikipedia.org/wiki/Random_walk_hypothesis

 

[wabbit]

Stormin'

I think you'll find that when it comes to finances and the markets, many "proper" processes have been bastardised to sound "funky" for the marketplace, when in fact they have very little resemblance to the true identity.

Take, for example:

Stochastics, which in the context of most charting applications has nothing to do with stochastic processes in the strict mathematical/statistical sense. The name was (allegedly) chosen because it happened to "sound good" and was part of the discussion the creators were having at the time.

A lot of stock market analysis systems which purport Monte Carlo systems or Monte Carlo analysis actually don't do anything close to Monte Carlo processing; they just perform some permutation/combination processing with little regard to randomness or proper sampling techniques.

Some Neural networks for financial applications are nothing but new-data curve fitting techniques. NN, especially PNNs "learn", not just plough through every possibility in something akin to a brute-force attack.


I think we have to remember that a lot of the success of the "system writers" and "indicator builders" is on making their product sound technical, when in fact, quite often, the opposite is true.

As the markets involve humans, and humans have been shown through hundreds (thousands?) of scientific studies to be incapable of being truly random, then markets are not going to be truly random either. I have always been dubious of the direct applicability of Brown, Wiener and Markov to the markets, and vice versa, "Lies, damn lies and statistics!"


wabbit

 

[pilbara]

Some Neural networks for financial applications are nothing but new-data curve fitting techniques. NN, especially PNNs "learn", not just plough through every possibility in something akin to a brute-force attack.

if it's possible to calculate every possibility within a short enough time, then I think it's worth doing, rather than take a sample. We have to make the most of the computer's strengths. Like how the chess computer Deep Thought/Blue had a massive brute force advantage to calculate all positions to a certain depth, which then allowed intelligent moves to emerge naturally.

 

[enigmatic]

I have to main comments to make..

The market is in no way random, randomness it self is a fallacy the market is directed by millions of individual people and events. However predicting the outcome of each individual person and event is mind blowingly Improbably.

When you are making these fictional trades do you not believe that your own trades if entered into the market will change the overall outcome of the days event possibly triggering an infinite number of varying outcomes which you can't predict.

Not saying there is definitely a possiblity that you could test a system which get 10,000% percent per day anything is technically possible with the limitations of total world market capital for x period of time. This however doesn't mean that x+y days your net gain will not be back down to 10%

plus if i had a system like this i would definitely not be wasting my time on aussie stock forum no matter how helpful it has been.

I would be straight out get a 1mil plus margin long and come back in 10years telling everyone about your Billion dollars you have.