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

    • TDUP ThredUp stock, watch for a top of range breakout above 2.94 at https://stockconsultant.com/?TDUP
    • Thx for reminding us... I don't bang that drum often enough anymore Another part for consideration is who that money initially went to...
    • TDUP ThredUp stock, watch for a top of range breakout above 2.94 at https://stockconsultant.com/?TDUP
    • How long does it take to receive HFM's withdrawal via Skrill? less than 24H?
    • My wife Robin just wanted some groceries.   Simple enough.   She parked the car for fifteen minutes, and returned to find a huge scratch on the side.   Someone keyed her car.   To be clear, this isn’t just any car.   It’s a Cybertruck—Elon Musk's stainless-steel spaceship on wheels. She bought it back in 2021, before Musk became everyone's favorite villain or savior.   Someone saw it parked in a grocery lot and felt compelled to carve their hatred directly into the metal.   That's what happens when you stand out.   Nobody keys a beige minivan.   When you're polarizing, you're impossible to ignore. But the irony is: the more attention something has, the harder it is to find the truth about it.   What’s Elon Musk really thinking? What are his plans? What will happen with DOGE? Is he deserving of all of this adoration and hate? Hard to say.   Ideas work the same way.   Take tariffs, for example.   Tariffs have become the Cybertrucks of economic policy. People either love them or hate them. Even if they don’t understand what they are and how they work. (Most don’t.)   That’s why, in my latest podcast (link below), I wanted to explore the “in-between” truth about tariffs.   And like Cybertrucks, I guess my thoughts on tariffs are polarizing.   Greg Gutfield mentioned me on Fox News. Harvard professors hate me now. (I wonder if they also key Cybertrucks?)   But before I show you what I think about tariffs… I have to mention something.   We’re Headed to Austin, Texas This weekend, my team and I are headed to Austin. By now, you should probably know why.   Yes, SXSW is happening. But my team and I are doing something I think is even better.   We’re putting on a FREE event on “Tech’s Turning Point.”   AI, quantum, biotech, crypto, and more—it’s all on the table.   Just now, we posted a special webpage with the agenda.   Click here to check it out and add it to your calendar.   The Truth About Tariffs People love to panic about tariffs causing inflation.   They wave around the ghost of the Smoot-Hawley Tariff from the Great Depression like it’s Exhibit A proving tariffs equal economic collapse.   But let me pop this myth:   Tariffs don’t cause inflation. And no, I'm not crazy (despite what angry professors from Harvard or Stanford might tweet at me).   Here's the deal.   Inflation isn’t when just a couple of things become pricier. It’s when your entire shopping basket—eggs, shirts, Netflix subscriptions, bananas, everything—starts costing more because your money’s worth less.   Inflation means your dollars aren’t stretching as far as they used to.   Take the 1800s.   For nearly a century, 97% of America’s revenue came from tariffs. Income tax? Didn’t exist. And guess what inflation was? Basically zero. Maybe 1% a year.   The economy was booming, and tariffs funded nearly everything. So, why do people suddenly think tariffs cause inflation today?   Tariffs are taxes on imports, yes, but prices are set by supply and demand—not tariffs.   Let me give you a simple example.   Imagine fancy potato chips from Canada cost $10, and a 20% tariff pushes that to $12. Everyone panics—prices rose! Inflation!   Nope.   If I only have $100 to spend and the price of my favorite chips goes up, I either stop buying chips or I buy, say, fewer newspapers.   If everyone stops buying newspapers because they’re overspending on chips, newspapers lower their prices or go out of business.   Overall spending stays the same, and inflation doesn’t budge.   Three quick scenarios:   We buy pricier chips, but fewer other things: Inflation unchanged. Manufacturers shift to the U.S. to avoid tariffs: Inflation unchanged (and more jobs here). We stop buying fancy chips: Prices drop again. Inflation? Still unchanged. The only thing that actually causes inflation is printing money.   Between 2020 and 2022 alone, 40% of all money ever created in history appeared overnight.   That’s why inflation shot up afterward—not because of tariffs.   Back to tariffs today.   Still No Inflation Unlike the infamous Smoot-Hawley blanket tariff (imagine Oprah handing out tariffs: "You get a tariff, and you get a tariff!"), today's tariffs are strategic.   Trump slapped tariffs on chips from Taiwan because we shouldn’t rely on a single foreign supplier for vital tech components—especially if that supplier might get invaded.   Now Taiwan Semiconductor is investing $100 billion in American manufacturing.   Strategic win, no inflation.   Then there’s Canada and Mexico—our friendly neighbors with weirdly huge tariffs on things like milk and butter (299% tariff on butter—really, Canada?).   Trump’s not blanketing everything with tariffs; he’s pressuring trade partners to lower theirs.   If they do, everybody wins. If they don’t, well, then we have a strategic trade chess game—but still no inflation.   In short, tariffs are about strategy, security, and fairness—not inflation.   Yes, blanket tariffs from the Great Depression era were dumb. Obviously. Today's targeted tariffs? Smart.   Listen to the whole podcast to hear why I think this.   And by the way, if you see a Cybertruck, don’t key it. Robin doesn’t care about your politics; she just likes her weird truck.   Maybe read a good book, relax, and leave cars alone.   (And yes, nobody keys Volkswagens, even though they were basically created by Hitler. Strange world we live in.) Source: https://altucherconfidential.com/posts/the-truth-about-tariffs-busting-the-inflation-myth    Profits from free accurate cryptos signals: https://www.predictmag.com/       
×
×
  • Create New...

Important Information

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