Re^5: AI Neural Networks based Prediciton

The common approach is to train your network on the data you have, and then use the last data item as the goal.

In your example, you would train your network on the days for 2010203, 2010204, 2010205, and then test it (for example) against 2010206.

Soon after, you will encounter the miracle of Overfitting your model to your training data.

Also, you will find that if (say) neural networks were good at predicting "the market", everybody would already be using them.

Comment on Re^5: AI Neural Networks based Prediciton

Replies are listed 'Best First'.
Re^6: AI Neural Networks based Prediciton by kulls (Hermit) on Sep 17, 2014 at 09:39 UTC
Hi, Thanks. Can you suggest me with example what would be a input and output for stock data ? Once I get it correctly, then I will add training sets in multiple source to overcome "Overfitting". Please bring me up from basic. Thanks, Raja K	[reply]
Re^7: AI Neural Networks based Prediciton by Corion (Patriarch) on Sep 17, 2014 at 10:17 UTC
You already have input and output for stock data in Re^4: AI Neural Networks based Prediciton. The trick is to use half (or 90% ) of your data as input data and the rest as output data.	[reply]
Re^8: AI Neural Networks based Prediciton by kulls (Hermit) on Sep 17, 2014 at 10:51 UTC
Hi, thanks, I got it that date as input and the stock data as output. let me try to compute the value Raja K	[reply]