The Altair Community is migrating to a new platform to provide a better experience for you. In preparation for the migration, the Altair Community is on read-only mode from October 28 - November 6, 2024. Technical support via cases will continue to work as is. For any urgent requests from Students/Faculty members, please submit the form linked here

time series predicting the future price

bdlagnobdlagno Member Posts: 3 Contributor I
edited September 2019 in Help
Hello all,

I just finished watching both youtube video of how to forecast prices https://www.youtube.com/watch?v=w0vSSEq2bn0 . However, my question is where can i find the next days forecasted/predicted price in rapidminer. To clarify. lets say my data ends on April 16,2014 I want rapidminer to predict the next days price April 17,2014. How to I achieve this.

thank you
Tagged:

Answers

  • Tair0Tair0 Member Posts: 2 Contributor I
    I have same question, could somebody tell me please how to forecast a few next days ?

  • MartinLiebigMartinLiebig Administrator, Moderator, Employee-RapidMiner, RapidMiner Certified Analyst, RapidMiner Certified Expert, University Professor Posts: 3,533 RM Data Scientist
    I think you need the series extension to do the things tom did there.

    ~Martin
    - Sr. Director Data Solutions, Altair RapidMiner -
    Dortmund, Germany
  • Tair0Tair0 Member Posts: 2 Contributor I
    Yes i installed Series extension. Problem is, no matter which operator I use, result table is still in form :

    ID;      Label;        Predicted Label;        Variables ........


    How to build model which can forecast bigger horizon than 1 ?  With result table that looks like:

    ID;      Predicted Label
    n+1          xyz
    n+2          xfka
    n+3          ....

    etc.

    With unknow variables for forecasted variables, just with learned model to catch Trend and seasonability during year ?

    Dont need to forecast exact values, only direction of further development.  :)
  • MartinLiebigMartinLiebig Administrator, Moderator, Employee-RapidMiner, RapidMiner Certified Analyst, RapidMiner Certified Expert, University Professor Posts: 3,533 RM Data Scientist
    Hi,

    just a short answer because i need to go:
    The trick is windowing. You create a table like this


    label  var1_n-1, var2_n-1, var2_n-1,

    then you can do it. Obviously the window can be longer than one and also contain more complex things.

    ~Martin
    - Sr. Director Data Solutions, Altair RapidMiner -
    Dortmund, Germany
Sign In or Register to comment.