Portal de Periódicos da CAPES

Isotonic boosting classification rules

2020; Springer Science+Business Media; Volume: 15; Issue: 2 Linguagem: Inglês

10.1007/s11634-020-00404-9

1862-5347

David Conde, Miguel A. Fernández, Cristina Rueda, Bonifacio Salvador,

Bayesian Modeling and Causal Inference

In many real classification 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.