1
$\begingroup$

I have a data set with 3 independent variables and 1 dependent variable. The dependent is play_golf, the independents are Humidity, Pending_Chores, Wind. I want to aggregate the probability of playing golf based on those rules of multiple trees. So again, play_golf (this is the dependent value), and there are three independent variables Humidity(High, Medium, Low), Pending_Chores(Taxes, None, Laundry, Car Maintenance) and Wind (High, Low). A rule would be like (IF humidity = "High" AND pending_chores = "None" AND Wind = "High" THEN play_golf = 77% ).

I was thinking that random forest would weight the rules somehow on the collection of trees and give a probability. But if that doesn't make sense, then can you just tell me how to get the decision rules with one tree and I will work from that. I believe am I talking about a decision tree vector? I'm not sure.

$\endgroup$
  • 1
    $\begingroup$ Have your tried CHAID? $\endgroup$ – Vishal Apr 14 '16 at 0:15
1
$\begingroup$

Have a look on HMM (Hidden Markov Model) also. A concrete example Of HMM is available in wikipedia. Decision tree is better in generalising and applying learned data in another context and a Markov-model is better to recall the exact learned machine state.

$\endgroup$
  • $\begingroup$ Not what I was looking for but this gave me a direction to go on to follow a similar problem $\endgroup$ – big_mike_boiii Apr 27 '16 at 23:21

Your Answer

By clicking “Post Your Answer”, you agree to our terms of service, privacy policy and cookie policy

Not the answer you're looking for? Browse other questions tagged or ask your own question.