Discussion:
New data mining technique: hidden decision trees
(too old to reply)
Vincent Granville
2009-03-21 19:27:43 UTC
Permalink
Hidden Decision Trees is a statistical and data mining methodology (just
like logistic regression, SVM, neural networks or decision trees) to
handle problems with large amounts of data, non-linearities and strongly
correlated dependent variables.

The technique is easy to implement in any programming language. It is more
robust than decision trees or logistic regression. Implementations
typically rely heavily on large, granular hash tables.

No decision tree is actually built (thus the name hidden decision trees),
but the final output of an hidden decision tree procedure consists of a
few hundred nodes from multiple non-overlapping small decision trees. Each
of these parent (invisible) decision trees corresponds e.g. to a
particular type of fraud, in fraud detection models. Interpretation is
straightforward, in contrast with traditional decision trees.


Please share your thoughts, how could this be implemented in SAS, or read
comments at http://www.analyticbridge.com/profiles/blogs/hidden-decision-
trees-a
d***@YAHOO.COM
2009-03-27 20:30:50 UTC
Permalink
since your algorithm is proprietary, nobody can help right now unless you
share the algorithm. Is it something related to Ensembled methods?

If you would like to share your algorithm, I am willing to implement it in
SAS. I have pretty strong programming skills in SAS. Please check out my
blog to confirm it.

sas-programming.blogspot.com


On Sat, 21 Mar 2009 15:27:43 -0400, Vincent Granville
Post by Vincent Granville
Hidden Decision Trees is a statistical and data mining methodology (just
like logistic regression, SVM, neural networks or decision trees) to
handle problems with large amounts of data, non-linearities and strongly
correlated dependent variables.
The technique is easy to implement in any programming language. It is more
robust than decision trees or logistic regression. Implementations
typically rely heavily on large, granular hash tables.
No decision tree is actually built (thus the name hidden decision trees),
but the final output of an hidden decision tree procedure consists of a
few hundred nodes from multiple non-overlapping small decision trees. Each
of these parent (invisible) decision trees corresponds e.g. to a
particular type of fraud, in fraud detection models. Interpretation is
straightforward, in contrast with traditional decision trees.
Please share your thoughts, how could this be implemented in SAS, or read
comments at http://www.analyticbridge.com/profiles/blogs/hidden-decision-
trees-a
s***@gmail.com
2018-05-27 18:06:32 UTC
Permalink
yes do you have detailed description
Post by Vincent Granville
Hidden Decision Trees is a statistical and data mining methodology (just
like logistic regression, SVM, neural networks or decision trees) to
handle problems with large amounts of data, non-linearities and strongly
correlated dependent variables.
The technique is easy to implement in any programming language. It is more
robust than decision trees or logistic regression. Implementations
typically rely heavily on large, granular hash tables.
No decision tree is actually built (thus the name hidden decision trees),
but the final output of an hidden decision tree procedure consists of a
few hundred nodes from multiple non-overlapping small decision trees. Each
of these parent (invisible) decision trees corresponds e.g. to a
particular type of fraud, in fraud detection models. Interpretation is
straightforward, in contrast with traditional decision trees.
Please share your thoughts, how could this be implemented in SAS, or read
comments at http://www.analyticbridge.com/profiles/blogs/hidden-decision-
trees-a
Loading...