A Predictive Model of Ride Satisfaction in Mass Transit Users

We describe a model for predicting subjective user satisfaction based on objective ride conditions. The model takes ride features (e.g., duration, crowding, waiting time) as inputs and estimates users’ single-ride satisfaction. This model enables transit authorities to predict the effect of service changes on user satisfaction. This in turn makes it possible to compare multiple candidate system configurations to determine which would yield the highest level of satisfaction. Using a sample of mass rapid transit users (n=641), the model is first trained then validated against unseen data. Prediction uncertainty is accounted for using a residual term. We also provide an example of how this model can be used to derive predictions, using artificial data.