@inproceedings{e673616996974debba109efa7f4c5977,
title = "Red-RF: Reduced Random Forest for Big Data Using Priority Voting & Dynamic Data Reduction",
abstract = "Random Forests have been used as effective ensemble models for classification. We present in this paper a new type of Random Forests (RFs) called Red(uced) RF that adopts a new dynamic data reduction principle and a new voting mechanism called Priority Vote Weighting (PV) which improve accuracy, execution time and AUC values compared to Breiman's RF. Red-RF also shows that the strength of a random forest can increase without noticeably increasing correlation between the trees. We then compare performance of Red-RF and Breiman's RF in 8 experiments that involve classification problems with datasets of different sizes. Finally, we conduct 2 additional experiments that involve considerably big datasets with one million points in each.",
keywords = "big data, classification, random forests, weighted voting",
author = "Hussein Mohsen and Hasan Kurban and Kurt Zimmer and Mark Jenne and Dalkilic, {Mehmet M.}",
note = "Publisher Copyright: {\textcopyright} 2015 IEEE.; 4th IEEE International Congress on Big Data, BigData Congress 2015 ; Conference date: 27-06-2015 Through 02-07-2015",
year = "2015",
month = aug,
day = "17",
doi = "10.1109/BigDataCongress.2015.26",
language = "English",
series = "Proceedings - 2015 IEEE International Congress on Big Data, BigData Congress 2015",
publisher = "Institute of Electrical and Electronics Engineers Inc.",
pages = "118--125",
editor = "Latifur Khan and Carminati Barbara",
booktitle = "Proceedings - 2015 IEEE International Congress on Big Data, BigData Congress 2015",
address = "United States",
}