Support vector logistic regression model with exact predictors and fuzzy responses

چکیده مقاله

A simple method is proposed in this paper for estimating the fuzzy logistic regression model adopted with support vector machines. The proposed method is robust against the outliers in cases that the predictors are exact quantities and the responses are fuzzy data. For this purpose, the unknown center, left, and right spreads of fuzzy regression coefficients were estimated via a separated three-stage estimation procedure. The performance of the proposed method was also compared with similar methods in terms of some common goodness-of-fit criteria used in fuzzy regression analysis. The numerical results revealed that the proposed fuzzy (non-linear) logistic regression model can offer sufficiently accurate results compared to other methods.