Thanks for the advice Kazam, I think I'm fairly set on looking at some form of genetic algorithm, ECGP looks the most promising. It's just my coding skills aren't that great and ANNs are fairly new to me. I am having some trouble with choosing the function set. Correct me if I am wrong but this a set of all possible functions for mapping nodes to each other? So I would specify a random distribution of input weights and the terminal set would contain all the node transfer & activation functions? Assign them uniform probabilities with the sum of the probabilities of sets F and T being 1. The optimization of the input weights would happen using SA or PSO thou? This resultant optimized best fit tree would be passed back to build a new PPT?

On a seperate note, the Uni library has all the editions of the European Conference on Genetic Programming from 1998 to 2004. Think they might be worth a read? They've also got a copy of 'Genetic programming and evolvable machines' by Dordrecht : Kluwer Academic Publishers, c2000 that I'm thinking about taking out.

mrwobbles

Don't start from ECGP. Start from something simple like designing NN using Genetic Programming or Gen Expression Programming. There are ready to use classes which implement those methods.

For example:

I don't know if there is a freely available implementation of ECGP, but there's one of ECGA /ECGP is based on ECGA/:

But like I said, skip ECGP/ECGA for now.

EDIT

As for the books - leave the conference materials for later /don't try to learn everything about NN's and Evolutionary Algorithms, focus on tools that might be useful for trading - time series prediction and decision making/.

Start from the "Field guide to genetic programming" that is free to download /I posted a link some pages ago/.

any neural network depends on how you choose the samples. i believe this question bother you too.

i build some eas use neural networks. but i havn't found a good sample prepare way.

here , i tell you my sample choose way, i 'm waiting for yours.

use three bars as the sample, the next bar as the result.

use few bars as the basewindow, and few bars as the feature window, set some feature value like ma value close price openprcie etc. any indicator you can use as the feature.

I tested this EA and found it doesn't produce the results that he is claiming. Very small profits, and huge losses. After several days of testing and working with the company, this EA couldn't produce results for more than a week or two at a time.

They claim to have a neural net in the MQ4 language, no dll. I find this very unlikely.

I asked for a refund and he would not give it to me. SCAMMER!!!!!

I'm not sure if this will be of any use to anyone but I found a GA toolkit for MATLAB called SGALAB. Anyway here's the link.

please googling and find the forum before you buy some fx product , sometimes commercial product on the net is free

===================
Forex Indicators Collection

Its very possible for someone to code a Neural network in mql. For Example:

NeuroProba Metatrader MQ4 Indicators Forex Trading Systems - XEATrade - Metatrader, Metastock, Tradestation, Amibroker - indicators, expert

My experience so far is don't bother predicting price with them. That would just be insanely stupid if you could really find one that could do that. Everyone would have it.

The best way to make a NN that is successful in trading is to use it to pick tops and bottoms. For example, feed it any current open position, the 5 previous OHLC values, 5 previous 20EMA values and maybe 5 previous stochastic values. Then have it tell you whether you should, go long, go short, close long, close short or do nothing.

As far as algorithms go, there are some interesting suggestions on this post and I can't wait to look at them and decide that I don't have a clue whats going on and give up trying to code one.

I am currently toying with TradeSolutions. It seems to offer some promise in developing Neural Nets that could be used in metatrader(I THINK it can export a DLL of the Neural Network you created, I am not quite sure yet, haven't figured that much out with it yet.)

Thanks for highlighting in this forum that NN does not perform to expectations. It is "scary" that the innocent public is conned by scammers.

In fact, I am searching for a commercial EA that produces results consistently, but held back bcos of these scams and hope that some members will come across some genuine ones.

I am a sucker when I see a good coders work

____________________________

This site, even if it does not have obvious direct connection to trading, contains "An Open Source Neural Networks C++ Library" and some very good coding : Flood: An Open Source Neural Networks C++ Library

Enjoy

is there a NN that can attempt to predict next # in a #'s series...like:
3,7,2,9,3,15....?