March 8, 2011

Blackbox trading Strategy using Rapidminer and R II



Long time without updating the blog for lack of time (again) due to new professional and personal challenges. Continuing with the strategy of Black Box, thanks to recommendations made by several readers and the lack of time to make a good tutorial of the model, I’m going to make available the file with a new version expecting new interesting and rewarding comments in order to improve the model. Actually the main problems in the strategy (commented by the users) are:
  • -          The overlapping between test, and evaluation, (solution, avoid this overlapping reduce test time)
  • -          The function maximization is based on profits (other possibilities are possible, working on it)
  • -          Risk management (related)
  • -          You cannot  select in an easy way the stock name (working on it)
  • -          No portfolio management
  • -          Low success in the prediction.

The archive can be downloaded free in this link. Please send me your comments, your modifications and suggestion …Publicar entrada
aT

9 comments:

  1. UnknownMarch 29, 2011 at 3:22 AM

    Hi,

    nice work. You can easily set the stock name:
    - connect a set macro to the input
    - name it inputSymbol, set the value to the desired ticker
    - connect the input to the R script
    - set the inputs in the R script to inputSymbol
    - modify the R script: change the symbol variable to input Symbol like so:
    # Parameters
    SymbolName=inputSymbol

    Also you can modify the start date, second date this way. And a lot of other things like what indicators you want to use.

    I liked this post very much, thanks for sharing.

    ivo

    ReplyDelete
  2. UnknownMarch 29, 2011 at 5:26 AM

    I was wrong actualy. You have to read a csv file of some sort to put variables into the R script.

    ReplyDelete
  3. a PhysicistApril 2, 2011 at 12:49 AM

    thanks for your comment, I agree with you the best way is to read a csv from a R or for Rapidminer.

    ReplyDelete
  4. YakitoOctober 23, 2011 at 4:05 PM

    Oh my god, after 3 hours I got a "not enough memory" message....time to upgrade.

    What machine are you using?
    Thanks for posting all these interesting posts.

    ReplyDelete
  5. a PhysicistNovember 5, 2011 at 4:21 PM

    Hi some times we obtain this error, but it is not usual, you can increase the memory of the Rapidminer to 2 Gigabytes, you can modify it inside the rapidminer startup script

    ReplyDelete
  6. JasonJune 29, 2012 at 7:39 AM

    Hi,
    I can read a csv file and use it in the R script. The R script generates a new csv, but I cannot prepare the output in a format that would be good for RapidMiner... Do you know how the csv should be in the output variable so that RM could handle it?
    Thanks,
    Jason

    ReplyDelete
  7. UnknownDecember 11, 2012 at 5:55 AM

    Hi
    We (myself and Ralf Klinkenberg from Rapid-i) are in the process of putting a rapidminer use case book together. Actually, we are nearly coming towards the final stages of reviewing phase and accepting 20 chapters. Unfortunately the proposed financial data mining chapter was not submitted by the author due to time constraints. Ralf and I both really like your blog and were wondering whether you are interested in submitting a use case chapter. If you are interested and need further info then please contact me on "markus dot hofmann at itb dot ie"

    Best wishes

    Dr. Markus Hofmann

    ReplyDelete
  8. ilainahcadavidMarch 3, 2022 at 11:45 AM

    Playtech mobile casino - JeMhub
    Playtech is the world 공주 출장마사지 leader 속초 출장안마 in mobile casino gaming. This is 과천 출장샵 the platform for an industry leader, with 충주 출장샵 over 600 mobile casino games. With more than 1300 서산 출장샵 games

    ReplyDelete
  9. CWG MarketsApril 20, 2022 at 2:51 AM

    I located one reliable example of this fact through this blog website. I am mosting likely to use such information now. Cfd Trading For Beginners

    ReplyDelete