Machine-learning techniques are increasingly being applied in the areas of exploratory data analysis, prediction, and classification. At the same time that analytical techniques are expanding, new conceptual approaches to the modeling of travel are emerging in an effort to improve travel demand forecasting and better assess the impacts of emerging transportation policy. In particular, the shift toward activity-based travel analysis has led to the development of activity scheduling models. One of the key features of emerging models of this type is the attempt to simulate the order in which activities are added during a continuous process of schedule construction. In practice, a fixed order by activity type is often assumed; for example, work activities are planned first, followed by the planning of more discretionary activity types. By using observed data on the scheduling process from a small sample of households from Quebec City, Quebec, Canada, a neural network model that classifies activities according to the order in which they were planned, the planning time horizon (preplanned, planned, or impulsive), was developed. A variety of explanatory variables were used in the model related to individual-, household-, and activity-based characteristics such as spatial and temporal fixities. The model developed exhibited a relatively high degree of prediction with the test data, especially for the preplanned and impulsive categories of the planning time horizon. These results suggest that machine-learning algorithms could be used to predict the order in which activities are selected in emerging activity scheduling process models, thereby avoiding static assumptions related purely to activity type.
Samenvatting