Welcome to the Traders Laboratory.

Coding Forum Collaborate, receive help, or discuss indicators and other coding-related topics

Reply
Old 07-02-2010, 10:53 AM   #9

natedredd10's Avatar

Join Date: Dec 2009
Location: wny
Posts: 111
Ignore this user

Thanks: 2
Thanked 38 Times in 25 Posts

Re: Neural Networks and Genetic Optimizers

Quote:
Originally Posted by BlowFish »
I'd say just get some tools and start 'playing' you don't really need to know too much about exactly how neural networks work the real skill (and art) comes in picking what inputs to feed in and what you look for in the output. (predicting price, particularly a long way in to the future is about as tough a task as one could give a net).
The problem to me with retail software in this area is its using some strange assumptions as far as feature extraction. Its easy to argue that for ES, price is a feature, volume is a feature, cash index price is a feature of, the volume of GS is a feature of ES.
I don't see how you can make an argument though that the RSI, MA, slow stochastic of ES price is a feature...Its making a huge assumption there is predictive power in these things to start with and that they are something other than simple price summaries.
To me the whole interesting thing in this area is in ditching these old models of price prediction and going straight to the factors that we know matter and creating new models.
natedredd10 is offline  
Reply With Quote
Old 07-02-2010, 11:27 AM   #10

Join Date: Oct 2009
Location: Port St Lucie
Posts: 62
Ignore this user

Thanks: 13
Thanked 29 Times in 21 Posts

Re: Neural Networks and Genetic Optimizers

Blowfish - Glad you joined this post.

I picked Tradecision soley because it was offered by TD Ameritrade. As far as I can tell, no lead applications offer a 30 trial or month to month option so if you select a software at a price tag of 2K, it makes sense that it meets your needs.

Your outline on the NN is 100% accurate and I really don't care too much about the mathematics behind the model. Choosing good inputs and correct interrpretation of results and application of the final version to the trading world are the real hurdles.

Right now, I'm just toying around the software. Making a model based on inputs & time series(ie S&P 500 Index); optimizing inputs; creating the NN; applying to simulation.

The Improvian Language used by Tradecision is really simple; like easy language so it's simple to create functions; indicators etc.

RANGER
Ranger is offline  
Reply With Quote
Old 07-02-2010, 12:15 PM   #11

UrmaBlume's Avatar

Join Date: Apr 2008
Location: Las Vegas
Posts: 718
Ignore this user

Thanks: 88
Thanked 636 Times in 261 Posts

Re: Neural Networks and Genetic Optimizers

The most effective models we have built come from a cascade of technologies. An example of such a cascade would be a model developed by first optimizing input preprocessing and input selection with genetic algorithms.

Then input data is used to develop a model using technologies that develop their models through what is called feed back mathematics, machine learning. Neural Networks and certain regression packages are used for this phase. Genetic algorithms can be used in this process to select and optimize such parameters and the number of nodes in middle layers of NNs and the transfer fuctions that weigh and pass the data between them. Our most used inter-nodal transfer function is the long-tailed sigmoid.

After the model is developed its output can be further optimized using decision trees or rules generators.

This site is a good place to find articles on and vedors of such tools. Every year that have a competition that ranks tools according to class.

For genetic optimizations we have written our own.

For the modeling process we like MARS® (Multivariate Adaptive Regression Splines) from Salford Systems in San Diego. We have built an application that converts the final MARS function to Trade Station's Easy Language so that we can deploy these models so that they can make their predictions in real time with just a cut and paste.

For rules generation we use CART, again from Salford Systems described on their website as "a robust, easy-to-use decision tree that automatically sifts large, complex databases, searching for and isolating significant patterns and relationships." We also use WizWhy from WizSoft. WizWhy cost around $4k and has served us very well.

Our process is described here which is an update and rewrite of this thread here on TL.

Good Luck with your project

cheers
UB
UrmaBlume is offline  
Reply With Quote
The Following 2 Users Say Thank You to UrmaBlume For This Useful Post:
JBWTrader (07-18-2010), Ranger (07-03-2010)
Old 07-02-2010, 01:32 PM   #12

natedredd10's Avatar

Join Date: Dec 2009
Location: wny
Posts: 111
Ignore this user

Thanks: 2
Thanked 38 Times in 25 Posts

Re: Neural Networks and Genetic Optimizers

Quote:
Originally Posted by BlowFish »
Does anyone have recommendations for resources that cover the practical application of these sorts of tool?
Here are applications I've found that are market related, but nothing in the way of theory/concepts:
SVM on RSI
Support Vector Machine RSI System Quantum Financier

Decision tree bagging system on GLD
Max Dama on Automated Trading: Decision Tree Bagging System (R code)

this guy has a bunch of different algos on market data, some with code.
Intelligent Trading
natedredd10 is offline  
Reply With Quote
The Following 2 Users Say Thank You to natedredd10 For This Useful Post:
Ranger (07-02-2010), taq (07-02-2010)
Old 07-03-2010, 09:13 AM   #13

BlowFish's Avatar

Join Date: Mar 2007
Location: In Da House
Posts: 3,233
Ignore this user

Thanks: 129
Thanked 1,081 Times in 708 Posts

Re: Neural Networks and Genetic Optimizers

Quote:
Originally Posted by natedredd10 »
The problem to me with retail software in this area is its using some strange assumptions as far as feature extraction. Its easy to argue that for ES, price is a feature, volume is a feature, cash index price is a feature of, the volume of GS is a feature of ES.
I don't see how you can make an argument though that the RSI, MA, slow stochastic of ES price is a feature...Its making a huge assumption there is predictive power in these things to start with and that they are something other than simple price summaries.
To me the whole interesting thing in this area is in ditching these old models of price prediction and going straight to the factors that we know matter and creating new models.
Quite so! Feeding an RSI (of price) a MACD (of price) and a CCI (of price) into a net will not end well! Using a normalised MA to pre process price dat before using it as an input might be a step in the right direction.

Ranger keep us posted on how it goes.

Incidentally user forums and blogs for some of these packages are likely to be as good a place for practical advice on how to get the best from these sorts of tools. Most of the issues are not unique to financial time series so no reason not to cast your net wider (if you pardon the pun).

This is not a recommendation and it is years since I read it but I do recall getting a bit out of Amazon.com: Neural, Novel & Hybrid Algorithms for Time Series Prediction (9780471130413): Timothy Masters: Books (pretty sure I didn't pay 355 bucks for it though!).
BlowFish is offline  
Reply With Quote
Old 07-03-2010, 11:22 AM   #14

Join Date: Oct 2009
Location: Port St Lucie
Posts: 62
Ignore this user

Thanks: 13
Thanked 29 Times in 21 Posts

Re: Neural Networks and Genetic Optimizers

Hi Urma

I reviewed the resources provided by you in your posting; some are very interesting including the article "Is MARS better than Neural Networks". The article was within my technical range of understanding and I enjoyed the conclusions which are straight foward.

Why did you select MARS vs NN?

It appears from your work that you use tradestation. Perhaps the justification for using MARS vs a NN is because the output is a linear approximation that can used in TS signals rather than the blackbox? It appears that model development using MARS plainly requires more work and expertise - advanced users only? Please comment.

On your website I read something about normalization of inputs; I rechecked the site and couldn't find the sentence again but anyway, it would be interesting to understand how you normalize inputs such as volume; balance of trade. Can you share this information with us?

@BLOWFISH - same comment about normalizing goes to you.

Thanks all for your VERY VALUABLE input.
Ranger is offline  
Reply With Quote
The Following 2 Users Say Thank You to Ranger For This Useful Post:
jma (07-03-2010), UrmaBlume (07-03-2010)
Old 07-03-2010, 11:58 AM   #15

UrmaBlume's Avatar

Join Date: Apr 2008
Location: Las Vegas
Posts: 718
Ignore this user

Thanks: 88
Thanked 636 Times in 261 Posts

Re: Neural Networks and Genetic Optimizers

Quote:
Originally Posted by Ranger »
Hi UrmaI reviewed the resources provided by you in your posting; some are very interesting including the article "Is MARS better than Neural Networks". The article was within my technical range of understanding and I enjoyed the conclusions which are straight foward. Why did you select MARS vs NN?
It appears from your work that you use tradestation. Perhaps the justification for using MARS vs a NN is because the output is a linear approximation that can used in TS signals rather than the blackbox? It appears that model development using MARS plainly requires more work and expertise - advanced users only? Please comment.
On your website I read something about normalization of inputs; I rechecked the site and couldn't find the sentence again but anyway, it would be interesting to understand how you normalize inputs such as volume; balance of trade. Can you share this information with us?@BLOWFISH - same comment about normalizing goes to you.Thanks all for your VERY VALUABLE input.
Ranger,

Thank you for the kind words.

I am constantly amazed at what a small percentage of supposedly educated and power traders have any meaningful experience with these " intelligent power tools" of data processing.

As to the selection of MARS vs NN, we are versed in both but with out level of experience find MARS easier to use and the models easier to deploy. Of note is that the selection of NN or MARS is not nearly so important as the engineering of the preprocessing of the inputs and targets.

Of note also is that these projects involve several technologies other than just the tools that build the models. We use genetic survival of the fittest code that we have written in house to aid in input selction and preprocessing as well as decision trees and rules generators to help us get more value from the model's output.

As to preprocessing and normalization, depending on the project, the input data must be scaled to the targets, outliers in training data considered and sometimes removed, input data must be carefully weighed and selected based on its relevance to the target. As to normalization we have several criteria. For volume and volatility based inputs one our more important considerations is that the data be normalized for time of day.

This link describes an application that demonstrates both preprocessing and the ouput from intelligent agents. The price specific Trade Points that you see on the app are the output of such agents while such indicators as the percentage of commercial presence and commercial bias are time of day normalized inputs.

cheers

UB
UrmaBlume is offline  
Reply With Quote
Old 07-03-2010, 05:06 PM   #16

Join Date: Apr 2007
Location: Victoria,Canada
Posts: 536
Ignore this user

Thanks: 43
Thanked 65 Times in 51 Posts

Re: Neural Networks and Genetic Optimizers

Urmablume,
Thank you for weighing in and we appreciate any examples of practical applications of NN with existing "non-forecasting" studies.
Also, are there any retail products that you would prefer for NN processing?
waveslider is offline  
Reply With Quote

Reply

Thread Tools
Display Modes Help Others By Rating This Thread
Help Others By Rating This Thread:

Similar Threads
Thread Thread Starter Forum Replies Last Post
Today's Action by Intelligent/Predictive Agents UrmaBlume Trading and the Markets 139 09-07-2010 02:23 PM

All times are GMT -4. The time now is 06:53 AM.
Copyright ©2000 - 2018, Jelsoft Enterprises Ltd.
CS to VB integration by DeskLancer
©2006-2011 Traders Laboratory, All Rights Reserved.