Over the past few years, machine-learning techniques have expanded enormously. These approaches are increasingly being applied to traffic and transportation problems formerly reserved for formal statistical approaches such as discrete choice models. Part of the reason for this has to do with research trends, but there are some potential advantages associated with such techniques, including the ability to model nonlinear systems; the ease with which symbolic, nominal, or categorical variables can be included; and the ability of these methods to deal with noisy data. The use of two modeling techniques, the nested logit model and the multilayer perceptron artificial neural network, was investigated in terms of their applicability to the household vehicle choice problem. Both methods generated strong results, although the multilayer perceptron artificial neural network yielded better predictive potential.
Nested Logit Models and Artificial Neural Networks for Predicting Household Automobile Choices: Comparison of Performance
Transportation Research Record
Transportation Research Record: Journal of the Transportation Research Board ; 1807 , 1 ; 92-100
2002-01-01
Article (Journal)
Electronic Resource
English
British Library Conference Proceedings | 2002
|Pivoting from a known base when predicting choices using logit models
Elsevier | 2023
|Nested Logit Models Which Are You Using?
Transportation Research Record | 1998
|