What kind of model should I use

saman_de_jong
saman_de_jong New Altair Community Member
edited November 2024 in Community Q&A

I am new to the world of datamining and for a school project I have to do an exercise. I have 3 datasets with a total of over 100 variables. Out of these variables I have chosen a couple of relevant ones in regard to the case I am trying to solve. I want to find which ID's are corresponding to the chosen variables, what kind of model do I use to do so? :) 

Answers

  • MartinLiebig
    MartinLiebig
    Altair Employee
    Hi,

    have a look at: http://mod.rapidminer.com/

    Cheers,
    Martin
  • saman_de_jong
    saman_de_jong New Altair Community Member

    Looked into it, can't decide which one is the one to go with...

  • Thomas_Ott
    Thomas_Ott New Altair Community Member
    Man...that type of question is like opening a big can of data science whoop ass. The simple and nebulous answer is, it depends.

    Think about what you want to optimize on and the business case, then start with the plain vanilla algos like Decision Tree and K-nn. Optimize their parameters. Then evaluate their metrics, and then try different other algorithms. Something like a neural net or a support vector machine.