A More Interesting Prediction of Stock Price by Neural Network

After more tuning work on my very primary neural network to predict the Price of stock market, I got some interesting result on ^HSI. 3600 sample data were used to train the network this time, from Mar 9, 2005, backward 3600 days. Generalization was applied forward from Mar 10, 2005 to Aug 23, 2006.

It's a simple MLP network with 3-layers, the hidden layer has 10 nodes, and 1 node for output layer.

Here's the result:

Click on the picture to enlarge it

nn

And the zoom-in view, the result is also applied to the future (From Mar 10, 2005 to Aug 23, 2006 on this picture)

nn

Comments

1. Klaus Meffert -- 2006-06-07 09:00

What is the toolkit you used?

2. Caoyuan -- 2006-06-07 09:00

Did you mean the charting, or neural network toolkit? it's written from scratch by myself.

Maybe I'll apply jgap for the next step as the GA module.

3. Ulrich -- 2006-07-29 09:00

Hi there,

i tried to find a contact address on your website, but there is none. I'd like to know if you want to do a little link exchange. If you place a link to  http://www.activestocks.eu on your xwiki's "other trading application" section, i will be happy to link to your page.

Best regards, Keep up the good work, Ulrich ( activestocks.eu )

4. 朱坛超 -- 2007-07-22 09:00

交个朋友吧 qq：757305889