Jump to content

Welcome to the new Traders Laboratory! Please bear with us as we finish the migration over the next few days. If you find any issues, want to leave feedback, get in touch with us, or offer suggestions please post to the Support forum here.

  • Welcome Guests

    Welcome. You are currently viewing the forum as a guest which does not give you access to all the great features at Traders Laboratory such as interacting with members, access to all forums, downloading attachments, and eligibility to win free giveaways. Registration is fast, simple and absolutely free. Create a FREE Traders Laboratory account here.

mr-T

Neural / genetic algorithms for trading

Recommended Posts

Hi Everyone!

 

I'm new to this site. Found it whilst doing a google search for trading discussion forums and this one looked best amongst the available alternatives.

 

I am interested in developing a 'basic' trading program, capable of learning trading rules based on pattern recognition and performance evaluation. I know of a few neural network and genetic algorithms out there, and have heard of their application in financial trading, but I am new to these areas and really need some advice. I would be very interested in hearing from anyone who has successfully applied NNs or GPs to intra-day data for forecasting. Any information would be helpful as what I would really like to do is create a basic program that I can play with and build on as my knowledge develops.

 

Best regards,

 

mr-T

Share this post


Link to post
Share on other sites

I have some experience with neural networks and genetic programming although its been a few years since I've worked with them. You may want to look through the paper at the following link: Time Series Prediction Using Evolving Polynomial Neural Networks

 

The paper applies those techniques for time series forecasting. I don't think it would be too difficult to evolve a NN to predict one or two days out for a particular stock. An easier approach would be to evolve a NN that would generate a buy/sell waveform like an oscillator. Since it would be more closely tailored to the characteristics of the stock you are looking at it may be more accurate than traditional indicators.

Share this post


Link to post
Share on other sites

Hi DrkTrade,

 

Thanks for your reply and the link to the thesis!! I've just had a look at it and it looks very interesting and comprehensive. I have collected a few papers on NNs and GAs so far, but not this one. Many thanks indeed!

 

Best regards,

 

mr-T

Share this post


Link to post
Share on other sites

Hi mr-T,

You may or may not be aware of a book called The Encyclopedia Of Trading Strategies by Jeffrey Owen Katz Ph.D. to which there's also a companion CD available. As I'm working with this software to identify the strategy I want to use, I thought I let you know about it. He includes NN and GA. Looking at the book for once you might get ideas.

 

Healthy Profits!

 

Genki

Share this post


Link to post
Share on other sites
The paper applies those techniques for time series forecasting. I don't think it would be too difficult to evolve a NN to predict one or two days out for a particular stock.

 

You are right, to predict something that looks to be usable is not a problem - see the applets at the site about prediction using neural networks that includes sample data for trading. But this is not all - if the prediction looks to be sufficient, it is also necessary to develop entry and exit rules - and this can be more important than more exact prediction.

Share this post


Link to post
Share on other sites

Thanks for your comments Marobi. I'll take this on board. I had a look at the website, and it contains very interesting information. It's a shame there is no totorial on writing a basic NN code. Even pseudo code would provide useful insight.

 

Thanks

 

mr-T

Share this post


Link to post
Share on other sites

Hi Genki,

 

Thanks for the book recommendation. Following on from my previous post, does the CD contain generic code, or is it all 'black box'?

 

Thanks,

 

mr-T

Share this post


Link to post
Share on other sites

Join the conversation

You can post now and register later. If you have an account, sign in now to post with your account.
Note: Your post will require moderator approval before it will be visible.

Guest
Reply to this topic...

×   Pasted as rich text.   Paste as plain text instead

  Only 75 emoji are allowed.

×   Your link has been automatically embedded.   Display as a link instead

×   Your previous content has been restored.   Clear editor

×   You cannot paste images directly. Upload or insert images from URL.


  • Topics

  • Posts

    • Question: To those that had/have cancer, what were the signs that made you think “something is not right here” to make you go see a doctor? Answer: So, 5/25/2018, I woke up, got ready for work, and as I walked to my car, I started gagging. Like something was stuck in my throat and I needed to clear it. And then it went away.   But 10 minutes after that, I was T-boned at 40mph on the driver side door. But what made me see a doctor was while my muscles felt better and bruises were going away, the gagging still continued, I started having fevers, my neck felt swollen, I was having such a hard time breathing, and I'd have random sharp pains in my chest, but not from where the seat belt saved me.   2 weeks after the accident, I finally see an urgent care doctor, who looks me over, tells me I'm fine, but luckily requests a neck X-ray. And I ask for a chest X-ray, which he rolls his eyes but let me have (most of my pain was in the neck, so I understand).   The very next day, he calls and says “So, that chest X-ray shows there's a 4 inch mass on your heart and lungs, and your lungs have been filling up with fluid, as well as in your pericardial (heart) wall. We need you to come in tomorrow.”   Turns out the big mass, due to the accident, caused my heart and lungs to tear and fill with fluid, the swollen neck and gagging was caused by 2 metastasized tumors, and the fevers and weight loss were symptoms. Stage 4b Hodgkin's Lymphoma.   But thankfully, we went very aggressive with chemo (and had a lot of bad side effects that don't normally happen to patients), and now I'm about 16 months cancer-free. Yay lucky X-rays! Rachel Jurina, Quora Source: https://www.quora.com/To-those-that-had-have-cancer-what-were-the-signs-that-made-you-think-something-is-not-right-here-to-make-you-go-see-a-doctor   Profits from free accurate cryptos signals: https://www.predictmag.com/  
    • As a man, the reality of life is the harshest part. I don’t mind looking older or becoming weaker over time; it’s nature.   Have you ever heard that the only people who will be loved unconditionally are women and children? Men will only be loved as long as they can provide until they are no longer needed. It doesn’t matter if you already did your best to get your kids to the best school or get the best things for them, if you stop before they’re done with it, there will be no thank you. The only thing they will remember is that they have to quit school at 15, ignoring all the previous 15 years of life you provided for them. The only people who will accept you, no matter what, are your parents. But in this situation, you might be that ungrateful child.   EDIT: Wow, I didn’t think this would get so much attention.   For those who disagree, I can only say that everyone has their problem. If you don’t get the chance to face such a thing, be grateful. Remember, sometimes what you throw in the garbage is something that someone wishes ever to have.” – ElZee, Quora   Profits from free accurate cryptos signals: https://www.predictmag.com/    
    • The good thing i had noticed so far is that the traderpot value is also on the rise..
    • yup its a gradual rollout the right way in my opinion, its really good and its exciting for the sto in 2027
    • there is no avoiding loses to be honest, its just how the market is. you win some and hopefully more, but u do lose some. 
×
×
  • Create New...

Important Information

By using this site, you agree to our Terms of Use.