Looking for a partnership for AI algo.

Discussion in 'Hook Up' started by robthequant, Oct 2, 2018.

Thread Status:
Not open for further replies.
  1. Sprout

    Sprout

    #31     Oct 4, 2018
  2. gkishot

    gkishot

    So if in a downtrend market hypothetically speaking the price is falling for 10 min and rising sightly(!) for 1 min so that you have 1 in 10 chance of catching the upward trend (maybe even less b/c upward moves are smaller compared to downward moves). I guess your system is capable of doing amazingly accurate analysis of the incipient counter trends.
     
    #32     Oct 4, 2018
  3. MarkBrown

    MarkBrown

    ouch i got muh feelin's hurt. playin sum 80's trance musik to soothe tha pain...
     
    #33     Oct 4, 2018
  4. Contact @Robert Morse - one prominent ET member.Maybe he can offer something for you.
     
    #34     Oct 4, 2018
  5. Another name is probably @Matz
     
    #35     Oct 4, 2018
  6. I`m so happy with my if/then stuff.Any rate is ok, the only concern is that the broker won`t go under.
     
    #36     Oct 4, 2018
    MarkBrown likes this.
  7. MarkBrown

    MarkBrown

    contact rentec ask for jim best i can do for you.
     
    #37     Oct 4, 2018
  8. Well, it's not amazingly accurate, rather it's well trained. it's a genetically evolved neural net that can make quick decisions that is tuned to the order book and order flow on a tick data. Google scientific papers from 2008 to 2018 related to AI, machine learning, finance, and market making, and you'll see that progress in this field is well beyond moving average crossover from the 80's :)

    lol, you have sense of humor, so you're a good guy :thumbsup:
     
    #38     Oct 4, 2018
    MarkBrown likes this.
  9. MarkBrown

    MarkBrown

    did i mention i owned a cray t-90? just sayin back in tha day before i waz a haz ben - i rocked!

    so serious question "what is your drawdown" ?

    the billion dollar interview - can you apply this 6 mo project to the es futures with only 4 tick risk per trade and obtain 1.5 net profit factor?
     
    #39     Oct 4, 2018
  10. That's pretty cool. What did you use the t-90 for?

    As far as drawdowns - my software minimizes underwater equity curve and maximizes profit per trade using multivariate genetic optimization - there's a great book on the subject ;) My equity curves on Bitcoin basically look like straight lines, there's very little draw-dawn in forward testing. Basically close to 0, it makes profit every day - you may think I'm crazy but it's true, if I saw this myself, I would think it's curvefit-bullshit, so I don't blame you if you think the same. But it validates on forward testing with real money, but there are drawdowns because of low quality executions, slippage and busy exchange server - not able to execute on their quotes during busy times. There are per second request limits etc...

    You mentioned the "6 months" again :) This is not a "6 months" of corporate style work - I've worked for an investment bank in NYC, so I know how that is. I'm an entrepreneur and this is 6 months of 12 hours hard coding and hard study each day while loving what I'm doing... and including most weekends. One person can achieve amazing results.

    About es futures I don't know... when I looked, I saw there are fees that may kill this. I need to be close to 0 or be a market maker getting rebates for limit orders. That's why I want to explore the other side. I can't do this on retail.
     
    #40     Oct 4, 2018
Thread Status:
Not open for further replies.