Anyone doing any historical back testing?

Discussion in 'Crypto Assets' started by Cuddles, Dec 16, 2017.

  1. Cuddles

    Cuddles

    Which exchange did you get your data from?

    I need to draw a few plots.... I'm seeing some patterns.
     
  2. just21

    just21

    Cuddles likes this.
  3. Cuddles

    Cuddles

    Thank you
     
  4. Hello Here4money,

    I use CQG data feed and it is free if using NinjaTrader.

    I am happy you are seeing some patterns to back test.
     
  5. Yes. DTN IQFeed. No more than 6 months back, but high trade frequency and sample size. All intraday
     
  6. Hello digitalnomad,

    What do you mean by "but high trade frequency and sample size. All intraday" ?
     
  7. Thanks
     
  8. Not HFT, but frequently trade on same instrument allowing large sample size to analyze. I generally do this monthly in regards to statistical signifigance. Just collect real-time data until that point
     
  9. Thanks digitalnomad for response.

    I also trade intraday and I constant question the following "How many trades for this system I developed and backtested is statistically significance enough". I try to develop on recent data just to see the difference.

    I am not sure I understand your comment. Can you go in detail please?
     
  10. Sure. As much as I can. While I actually trade monthly, what I perceive to be the most optimal inputs for my algorithms, using my pricing model, I simultaneously run thousands of trade simulations across multiple instruments and time series. I choose the most optimal variation at discretion to trade live for the following month. Most would assume this by what I just typed, but the simulations take hours to run, and run on multiple machines :)
     
    Last edited: Dec 17, 2017
    #10     Dec 17, 2017
    SimpleMeLike likes this.