How to cite classification algorithm of raidminer

SA_HSA_H Member Posts: 29 Contributor II
edited October 2019 in Help
How I can cite decision tree, CHAID, Random Forest, Gradient boosted Trees in scientific research. I mean the scientific reference for implementation of the algorithm themselves not rapidminer as whole.

Best Answer

Answers

  • varunm1varunm1 Moderator, Member Posts: 1,207 Unicorn
    edited October 2019
    Hello @summer_helmi

    In scientific papers, especially when you talk about machine learning algorithms it is important to inform about hyperparameters. Most of the time it is not possible to cite exact algorithm papers as they are slightly modified versions in tools. If you want to cite you can look for base papers of these algorithms. Decision trees and random forest in rapidminer uses different backend algorithms based on the criterion "gain_ratio", "Information Gain", "gini_index" etc. These will trigger either CART or C4.5 algorithms based on selection. But these are modified versions as well.

    Citing rapidminer as software and providing a table with hyperparameters is stronger. If you really want to cite papers, you can cite the base decision tree papers related to C4.5 by Ross Quinlan or CART algorithms.

    For GBT, its H2o. "Malohlava, M., & Candel, A. (2017). Gradient boosting machine with H2O."

    Just my 2 cents. @mschmitz or @IngoRM any insights here?
    Regards,
    Varun
    https://www.varunmandalapu.com/

    Be Safe. Follow precautions and Maintain Social Distancing

  • SA_HSA_H Member Posts: 29 Contributor II
    Thank you for your reply. Indeed, I will cite rapidminer as software, but I need determined citation for the algorithms used within rapidminer. You may have a look for WEKA extension for rapidminer, and you will find inside each operator description, you will find the scientific reference.
  • varunm1varunm1 Moderator, Member Posts: 1,207 Unicorn
    edited October 2019
    Yep, I agree. The DT is a own implementation (learned from @mschmitz )of RM, so I tagged relevant people who might provide. I gave the GBT in RM based on H2O, so the reference I provided can be used.
    Regards,
    Varun
    https://www.varunmandalapu.com/

    Be Safe. Follow precautions and Maintain Social Distancing

  • sgenzersgenzer Administrator, Moderator, Employee, RapidMiner Certified Analyst, Community Manager, Member, University Professor, PM Moderator Posts: 2,959 Community Manager
    hi @summer_helmi I don't know the protocols for the journal(s) you're planning to publish but I would cite the code (and authors therewithin) via GitHub.
  • SA_HSA_H Member Posts: 29 Contributor II
    edited October 2019
    Please give an example for any Journal, for Random forest algorithm within rapidminer.
  • sgenzersgenzer Administrator, Moderator, Employee, RapidMiner Certified Analyst, Community Manager, Member, University Professor, PM Moderator Posts: 2,959 Community Manager
    edited October 2019
    so again it depends on your journal but just as an example this is MLA8. I am going to defer to academics on this forum for critique or affirmation :smile:

    Mierswa, Ingo, and Sebastian Land. β€œRandomForestLearner.java Source Code.” GitHub, RapidMiner, Inc., 6 Feb. 2019, github.com/rapidminer/rapidminer-studio/blob/3a2da3e40bbadaf5515e04093867798c27d0654d/src/main/java/com/rapidminer/operator/learner/tree/RandomForestLearner.java.


  • SA_HSA_H Member Posts: 29 Contributor II
    Thank you, do the authors are the same for any algorithm within rapidminer.
  • sgenzersgenzer Administrator, Moderator, Employee, RapidMiner Certified Analyst, Community Manager, Member, University Professor, PM Moderator Posts: 2,959 Community Manager
    thank you @varunm1. It has been a LONG time since I last cited sources for a research paper!
  • varunm1varunm1 Moderator, Member Posts: 1,207 Unicorn
    You are still good @sgenzer :smiley:
    Regards,
    Varun
    https://www.varunmandalapu.com/

    Be Safe. Follow precautions and Maintain Social Distancing

Sign In or Register to comment.