Alpha Skew Gaussian Naive Bayes Classifier

The main goal of this paper is to introduce a new procedure for a naive Bayes classifier, namely alpha skew Gaussian naive Bayes (ASGNB), which is based on a flexible generalization of the Gaussian distribution applied to continuous variables. As a direct advantage, this method can accommodate the possibility to handle with asymmetry in the uni or bimodal behavior. We provide the estimation procedure of this method, and we check the predictive performance when compared to other traditional classification methods using simulation studies and many real datasets with different application fields. The ASGNB is a powerful alternative to classification tasks when lie the presence of asymmetry of bimodality in the data and outperforms well when compared to other traditional classification methods in most of the cases analyzed.

Automated summary

The main goal of this paper is to introduce a new procedure for a naive Bayes classifier, called alpha skew Gaussian naive Bayes (ASGNB), which utilizes a flexible generalization of the Gaussian distribution on continuous variables. ASGNB is capable of handling asymmetry or bimodal behavior in the data and outperforms other traditional classification methods in terms of predictive performance.