RT info:eu-repo/semantics/article
T1 Isotonic boosting classification rules
A1 Conde del Río, David
A1 Fernández Temprano, Miguel Alejandro
A1 Rueda Sabater, María Cristina
A1 Salvador González, Bonifacio
AB In many real classi cation problems a monotone relation between some predictors and the classes may be assumed when higher (or lower) values of those predictors are related to higher levels of the response. In this paper, we propose new boosting algorithms, based on LogitBoost, that incorporate this isotonicity information, yielding more accurate and easily interpretable rules. These algorithms are based on theoretical developments that consider isotonic regression. We show the good performance of these procedures not only on simulations, but also on real data sets coming from two very different contexts, namely cancer diagnostic and failure of induction motors.
SN 1862-5347
YR 2020
FD 2020
LK http://uvadoc.uva.es/handle/10324/45327
UL http://uvadoc.uva.es/handle/10324/45327
LA spa
NO Advances in Data Analysis and Classification.  pag 1-25.
DS UVaDOC
RD 11-jul-2024