We introduce Random Multinomial Logit (RML), a general multi-class classifier based on an ensemble of multinomial logistic regression models, and apply it to the task of semantic image segmentation. The algorithm is simple, can be trained efficiently, and has near realtime runtime performance. RML combines the desirable properties of multinomial logistic regression, being stable and theoretical...

In air travel, an itinerary is a direct flight or sequence of connecting flights between two cities. The objective of itinerary market share estimation is to forecast market shares of competing itineraries. This paper examines and compares three different methods for itinerary market share estimation: multinomial logit models, artificial neural networks, and a custom model developed by the auth...

In order to design the traffic network more accurately, the bi-level programming model for the continuous network design problem based on the paired combinatorial Logit stochastic user equilibrium model is proposed in this study. In the model, the paired combinatorial Logit stochastic user equilibrium model which is used to characterize the route choice behaviors of the users is adopted in the ...

The Russian banking sector experienced considerable turmoil in the late 1990s, especially around the Russian banking crisis in 1998. The question is what types of banks are vulnerable to shocks and whether or not bank-specific characteristics can be used to predict vulnerability to failures. In this study we employ a parametric logit model and a nonparametric trait recognition approach to predi...

This thesis examines how to model the choice of individual travelers among various possible travel alternatives in the airline industry. A review of the models used to represent that choice situation in the Passenger OriginDestination Simulator (PODS) was undertaken for two reasons. First, the development of computational capabilities has lead to advancements in consumer choice theory that enab...

This paper empirically assesses the relative role of health plan prices, service quality and optional benefi ts in the decision to choose a health plan. We link representative German SOEP panel data from 2007 to 2010 to (i) health plan service quality indicators, (ii) measures of voluntary benefi t provision on top of federally mandated benefi ts, and (iii) health plan prices for almost all Ger...

This article proposes a method for multiclass classification problems using ensembles of multinomial logistic regression models. A multinomial logit model is used as a base classifier in ensembles from random partitions of predictors. The multinomial logit model can be applied to each mutually exclusive subset of the feature space without variable selection. By combining multiple models the pro...

The mixed logit model is considered to be the most promising state of the art discrete choice model currently available. Increasingly researchers and practitioners are estimating mixed logit models of various degrees of sophistication with mixtures of revealed preference and stated preference data. It is timely to review progress in model estimation since the learning curve is steep and the unw...