ENSEMBLE METHODS FOR RANKING DATA

Risultato della ricerca: Conference contribution

Abstract

The last years have seen a remarkable flowering of works about the use of decision trees for ranking data. As a matter of fact, decision trees are useful and intuitive, but they are very unstable: small perturbations bring big changes. This is the reason why it could be necessary to use more stable procedures, as ensemble methods, in order to find which predictors are able to explain the preference structure. In this work ensemble methods as BAGGING and Random Forest are proposed, from both a theoretical and computational point of view, for deriving classification trees when ranking data are observed. The advantages of these procedures are shown through an example on the SUSHI data set.
Lingua originaleEnglish
Titolo della pubblicazione ospiteBook of Short Papers
Pagine1-6
Numero di pagine6
Stato di pubblicazionePublished - 2017

Fingerprint

ranking
flowering
perturbation
method
decision

Cita questo

Plaia, A., & Sciandra, M. (2017). ENSEMBLE METHODS FOR RANKING DATA. In Book of Short Papers (pagg. 1-6)

ENSEMBLE METHODS FOR RANKING DATA. / Plaia, Antonella; Sciandra, Mariangela.

Book of Short Papers. 2017. pag. 1-6.

Risultato della ricerca: Conference contribution

Plaia, A & Sciandra, M 2017, ENSEMBLE METHODS FOR RANKING DATA. in Book of Short Papers. pagg. 1-6.
Plaia A, Sciandra M. ENSEMBLE METHODS FOR RANKING DATA. In Book of Short Papers. 2017. pag. 1-6
@inproceedings{851582b9a5c14296aee4f477d22eb2db,
title = "ENSEMBLE METHODS FOR RANKING DATA",
abstract = "The last years have seen a remarkable flowering of works about the use of decision trees for ranking data. As a matter of fact, decision trees are useful and intuitive, but they are very unstable: small perturbations bring big changes. This is the reason why it could be necessary to use more stable procedures, as ensemble methods, in order to find which predictors are able to explain the preference structure. In this work ensemble methods as BAGGING and Random Forest are proposed, from both a theoretical and computational point of view, for deriving classification trees when ranking data are observed. The advantages of these procedures are shown through an example on the SUSHI data set.",
keywords = "bagging, ensemble methods, random forest, ranking data",
author = "Antonella Plaia and Mariangela Sciandra",
year = "2017",
language = "English",
isbn = "978-88-99459-71-0",
pages = "1--6",
booktitle = "Book of Short Papers",

}

TY - GEN

T1 - ENSEMBLE METHODS FOR RANKING DATA

AU - Plaia, Antonella

AU - Sciandra, Mariangela

PY - 2017

Y1 - 2017

N2 - The last years have seen a remarkable flowering of works about the use of decision trees for ranking data. As a matter of fact, decision trees are useful and intuitive, but they are very unstable: small perturbations bring big changes. This is the reason why it could be necessary to use more stable procedures, as ensemble methods, in order to find which predictors are able to explain the preference structure. In this work ensemble methods as BAGGING and Random Forest are proposed, from both a theoretical and computational point of view, for deriving classification trees when ranking data are observed. The advantages of these procedures are shown through an example on the SUSHI data set.

AB - The last years have seen a remarkable flowering of works about the use of decision trees for ranking data. As a matter of fact, decision trees are useful and intuitive, but they are very unstable: small perturbations bring big changes. This is the reason why it could be necessary to use more stable procedures, as ensemble methods, in order to find which predictors are able to explain the preference structure. In this work ensemble methods as BAGGING and Random Forest are proposed, from both a theoretical and computational point of view, for deriving classification trees when ranking data are observed. The advantages of these procedures are shown through an example on the SUSHI data set.

KW - bagging

KW - ensemble methods

KW - random forest

KW - ranking data

UR - http://hdl.handle.net/10447/243820

M3 - Conference contribution

SN - 978-88-99459-71-0

SP - 1

EP - 6

BT - Book of Short Papers

ER -