Causation versus Prediction: Comparing Causal Discovery and Inference with Artificial Neural Networks in Travel Mode Choice Modeling

TL;DR

This paper compares causal discovery and inference methods with neural network prediction in modeling travel mode choice, highlighting the potential of causal approaches to deepen understanding of decision-making processes.

Contribution

It introduces a combined approach using causal discovery, inference, and neural networks to analyze travel mode choice, an area with limited prior causal modeling.

Findings

Trip distance and vehicle ownership are direct causes of mode choice.

Neural networks achieved over 70% prediction accuracy.

Causal modeling offers valuable insights into decision-making processes.

Abstract

This study compares the performance of a causal and a predictive model in modeling travel mode choice in three neighborhoods in Chicago. A causal discovery algorithm and a causal inference technique were used to extract the causal relationships in the mode choice decision making process and to estimate the quantitative causal effects between the variables both directly from observational data. The model results reveal that trip distance and vehicle ownership are the direct causes of mode choice in the three neighborhoods. Artificial neural network models were estimated to predict mode choice. Their accuracy was over 70%, and the SHAP values obtained measure the importance of each variable. We find that both the causal and predictive modeling approaches are useful for the purpose they serve. We also note that the study of mode choice behavior through causal modeling is mostly unexplored, yet it could transform our understanding of the mode choice behavior. Further research is needed to realize the full potential of these techniques in modeling mode choice.