Attitudes and Latent Class Choice Models using Machine Learning

Abstract

We present a method of efficiently incorporating attitudinal indicators in the specification of Latent Class Choice Models (LCCM), extensions of Discrete Choice Models (DCMs) that segment populations based on the assumption of preference similarities. We introduce Artificial Neural Networks (ANN) to formulate the latent variables constructs. This formulation overcomes structural equations in its ability to explore the relationship between the attitudinal indicators and the decision choice, given the machine learning (ML) flexibility and power to capture unobserved and complex behavioural features, such as attitudes and beliefs. All of this, while maintaining the consistency of the theoretical assumptions presented in the Generalized Random Utility model and the interpretability of the estimated parameters. We test our proposed framework for estimating a car-sharing service subscription choice with stated preference data. The results show that our proposed approach provides a complete and realistic segmentation, which helps design better policies.