Can ANN outsmart the market?


Can ANN outsmart the market?

To illustrate why NN is a difficult approach, I can show two examples:
One is this forum:
And this as another forum:

What I saw in those forums that there was a lot of enthusiasm at the beginning, but
the authors faced too much challenge. The initial network had no predictive power, and the enthusiasm failed,
and they gave up.
That is a bad omen for me.

Forecasting the stock market is really a very difficult task. But we learn this fact only by experience.
We think we can outsmart the market. But there are pitfalls.
Most of the pittfall come when the backtest works, but in real life, the network doesn’t produce.
But, I will leave this discussion later.

On the other hand, I could see somebody who successfully cracked the market with NN prediction.
He has an annual %gain of 88%.
This guy is the winner of the Automated Trading Championship-2007, and he uses NN.
The success of him is a fact that tinkering with NN may worth the time.


No Responses Yet to “Can ANN outsmart the market?”

  1. Leave a Comment

Leave a Reply

Fill in your details below or click an icon to log in: Logo

You are commenting using your account. Log Out /  Change )

Google+ photo

You are commenting using your Google+ account. Log Out /  Change )

Twitter picture

You are commenting using your Twitter account. Log Out /  Change )

Facebook photo

You are commenting using your Facebook account. Log Out /  Change )


Connecting to %s

%d bloggers like this: