Discrete choice modeling using Kernel Logistic Regression

Abstract

The Kernel Logistic Regression is a popular technique in machine learning. In this work this technique is applied to the field of discrete choice modeling. This approach is equivalent to specifying non-parametric utilities in random utility models. A Monte Carlo simulation experiment has been carried out to compare this approach with Multinomial Logit models, comparing the goodness of fit and the capability of obtaining the specified utilities.

Publication
Transportation Research Procedia

Related